Publications

@article{blanchard2018,

  author    = {Nathaniel Blanchard and

                Jeffery Kinnison and

                Brandon RichardWebster and

                Pouya Bashivan and

                Walter J. Scheirer},

  title     = {A Neurobiological Cross-domain Evaluation Metric for Predictive Coding Networks},

  journal   = {},

  volume    = {},

  year      = {2018},

  url       = {},

  timestamp = {},

  biburl    = {},

  bibsource = {}

}

@article{DBLP:journals/corr/abs-1805-11519,

  author    = {Pei Li and

               Loreto Prieto and

               Domingo Mery and

               Patrick J. Flynn},

  title     = {Face Recognition in Low Quality Images: {A} Survey},

  journal   = {CoRR},

  volume    = {abs/1805.11519},

  year      = {2018},

  url       = {http://arxiv.org/abs/1805.11519},

  archivePrefix = {arXiv},

  eprint    = {1805.11519},

  timestamp = {Wed, 06 Jun 2018 14:48:18 +0200},

  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1805-11519},

  bibsource = {dblp computer science bibliography, https://dblp.org}

}

@article {Shahbazi278515,

author = {Shahbazi, Ali and Kinnison, Jeffery and Vescovi, Rafael and Du, Ming and Hill, Robert and J{\"o}sch, Maximilian and Takeno, Marc and Zeng, Hongkui and da Costa, Nuno Ma{\c c}arico and Grutzendler, Jaime and Kasthuri, Narayanan and Scheirer, Walter J.},

title = {Flexible Learning-Free Segmentation and Reconstruction for Sparse Neuronal Circuit Tracing},

year = {2018},

doi = {10.1101/278515},

publisher = {Cold Spring Harbor Laboratory},

abstract = {Imaging is a dominant strategy for data collection in neuroscience, yielding 3D stacks of images that can scale to petabytes of data for a single experiment. Machine learning-based algorithms from the computer vision domain can serve as a pair of virtual eyes that tirelessly processes these images to automatically construct more complete and realistic circuits. In practice, such algorithms are often too error-prone and computationally expensive to be immediately useful. Therefore we introduce a new fast and flexible learning-free automated method for sparse segmentation and 2D/3D reconstruction of brain micro-structures. Unlike supervised learning methods, our pipeline exploits structure-specific contextual clues and requires no extensive pre-training. This approach generalizes across different modalities and sample targets, including serially-sectioned scanning electron microscopy (sSEM) of genetically labeled and contrast enhanced processes, spectral confocal reflectance (SCoRe) microscopy, and high-energy synchrotron X-ray microtomography (μCT) of large tissue volumes. Experiments on newly published and novel mouse datasets demonstrate the high biological fidelity and recall of the proposed pipeline, as well as reconstructions of sufficient quality for preliminary biological study. Compared to existing supervised methods, it is both significantly faster (up to several orders of magnitude) and produces high-quality reconstructions that are robust to noise and artifacts.},

URL = {https://www.biorxiv.org/content/early/2018/03/08/278515},

eprint = {https://www.biorxiv.org/content/early/2018/03/08/278515.full.pdf},

journal = {bioRxiv}

}

@article{DBLP:journals/corr/BowyerF16,

  author    = {Kevin W. Bowyer and

               Patrick J. Flynn},

  title     = {The {ND-IRIS-0405} Iris Image Dataset},

  journal   = {CoRR},

  volume    = {abs/1606.04853},

  year      = {2016},

  url       = {http://arxiv.org/abs/1606.04853},

  archivePrefix = {arXiv},

  eprint    = {1606.04853},

  timestamp = {Wed, 07 Jun 2017 14:42:19 +0200},

  biburl    = {https://dblp.org/rec/bib/journals/corr/BowyerF16},

  bibsource = {dblp computer science bibliography, https://dblp.org}

}

@article{DBLP:journals/corr/GrantF16,

  author    = {Jason M. Grant and

               Patrick J. Flynn},

  title     = {Hierarchical Clustering in Face Similarity Score Space},

  journal   = {CoRR},

  volume    = {abs/1605.06052},

  year      = {2016},

  url       = {http://arxiv.org/abs/1605.06052},

  archivePrefix = {arXiv},

  eprint    = {1605.06052},

  timestamp = {Wed, 07 Jun 2017 14:40:53 +0200},

  biburl    = {https://dblp.org/rec/bib/journals/corr/GrantF16},

  bibsource = {dblp computer science bibliography, https://dblp.org}

}

@article{vidalmata2021bridging,
title = {Bridging the Gap Between Computational Photography and Visual
Recognition},
author = {Rosaura G. VidalMata and
Sreya Banerjee and
Brandon RichardWebster and
Michael Albright and
Pedro Davalos and
Scott McCloskey and
Ben Miller and
Asong Tambo and
Sushobhan Ghosh and
Sudarshan Nagesh and
Ye Yuan and
Yueyu Hu and
Junru Wu and
Wenhan Yang and
Xiaoshuai Zhang and
Jiaying Liu and
Zhangyang Wang and
Hwann-Tzong Chen and
Tzu-Wei Huang and
Wen-Chi Chin and
Yi-Chun Li and
Mahmoud Lababidi and
Charles Otto and
Walter J. Scheirer},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence
(T-PAMI)},
volume = {43},
number = {12},
month = {December},
year = {2021}
}

@inproceedings{Shen_FG2021,

author = {Bingyu Shen and
Brandon RichardWebster and
Alice O'Toole and
Kevin Bowyer and
Walter J. Scheirer},
title = {A Study of the Human Perception of Synthetic Faces},
booktitle = {Proceedings of the IEEE Conference on Automatic Face and
Gesture Recognition (FG)},
year = {2021}
}

@article{SPETH2021103246,
title = {Unifying frame rate and temporal dilations for improved remote pulse detection},
journal = {Computer Vision and Image Understanding},
volume = {210},
pages = {103246},
year = {2021},
issn = {1077-3142},
doi = {https://doi.org/10.1016/j.cviu.2021.103246},
url = {https://www.sciencedirect.com/science/article/pii/S1077314221000904},
author = {Jeremy Speth and Nathan Vance and Patrick Flynn and Kevin Bowyer and Adam Czajka},
keywords = {Remote photoplethysmography, Face video, Physiological monitoring, Spatiotemporal modeling, Pulse detection},
abstract = {Remote photoplethysmography (rPPG) is the monitoring of blood volume pulse from a camera at a distance. 3-Dimensional Convolutional Neural Networks (3DCNNs) have shown promising performance on the rPPG task, although it is critical that we understand the impact of both video and model parameters. In this paper, we explore the effect of frame rate, temporal kernel width, and – more generally – temporal receptive field on the reliability of heart rate and waveform estimation carried out by 3DCNNs. We train and evaluate 32 3DCNNs with different temporal parameters on a new large-scale database for physiological monitoring in an interview scenario. We show that previous studies reporting null effects of frame rate changes on pulse estimators may no longer be valid when using CNNs, and decreasing the frame rate may actually improve performance. In particular, we found that models trained on videos with frame rates as low as 12.9 frames per second (fps) perform better than those trained on videos recorded at a full 90 fps, perhaps due to the temporal receptive fields becoming larger in time dimension when the fps decreases. Using this insight, we propose RemotePulseNet, a novel 3DCNN architecture that exploits temporally dilated convolutions with increasing dilation rate to drastically increase the receptive field. We compare its performance with that of recent state-of-the-art pulse estimation methods, and show that both RemotePulseNet and the low frame rate 3DCNNs produce high-quality pulse signals from faces captured under a challenging interview scenario. The source code and instructions for obtaining a copy of the test data are made available with this paper.}
}

@inproceedings{theisen2021automatic,
title={Automatic Discovery of Political Meme Genres with Diverse Appearances},
author={William Theisen and Joel Brogan and Pamela Bilo Thomas and
Daniel Moreira and Pascal Phoa and Tim Weninger and Walter Scheirer},
booktitle={International AAAI Conference on Web and Social Media (ICWSM)}
year={2021},
}

@ARTICLE{9164898,
  author={Fang, Zhaoyuan and Czajka, Adam and Bowyer, Kevin W.},
  journal={IEEE Transactions on Information Forensics and Security},
  title={Robust Iris Presentation Attack Detection Fusing 2D and 3D Information},
  year={2021},
  volume={16},
  number={},
  pages={510-520},
  doi={10.1109/TIFS.2020.3015547}}

@article{yankoski2021memes,
title={}Meme warfare: AI countermeasures to disinformation should focus on popular,
not perfect, fakes,
author={Yankoski, Michael, Scheirer, Walter and Weninger, Tim},
journal={Bulletin of the Atomic Scientists},
month={May},
year={2021},
publisher={Taylor \& Francis}
}

@inproceedings{Boult21,
author = {Terrance Boult and
Przemyslaw Grabowicz and
Derek Prijatelj and
Lawrence Holder and
Joshua Alspector and
Mohsen Jafarzadeh and
Touqeer Ahmad and
Akshay Dhamija and
Chunchun Li and
Steve Cruz and
Abhinav Shrivastava and
Carl Vondrick and
Walter J. Scheirer},
title = {Towards a Unifying Framework for Formal Theories of Novelty},
booktitle = {AAAI Conference on Artificial Intelligence (AAAI 2021)},
year = {2021},
}

@article {Banerjee2020.09.01.277657,
author = {Banerjee, Sreya and Alvey, Lauren and Brown, Paula and Yue,
Sophie and Li, Lei and Scheirer, Walter J.},
title = {An Assistive Computer Vision Tool to Automatically Detect
Changes in Fish Behavior In Response to Ambient Odor},
elocation-id = {2020.09.01.277657},
year = {2020},
doi = {10.1101/2020.09.01.277657},
publisher = {Cold Spring Harbor Laboratory},
journal = {bioRxiv}

@InProceedings{Shen_2021_WACV,
author = {Shen, Bingyu and Li, Boyang and Scheirer, Walter J.},
title = {Automatic Virtual 3D City Generation for Synthetic Data Collection},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications
of Computer Vision (WACV) Workshops},
month = {January},
year = {2021},
pages = {161-170}
}

@article{bowyer2020criminality,
title={The Criminality From Face Illusion},
author={Kevin W. Bowyer and Michael King and Walter Scheirer and Kushal Vangara},
journal={IEEE Transactions on Technology and Society (T-TS)},
volume={1},
number={4},
month={December},
year={2020},
}

@inproceedings{Biderman20_ICBINB,
author = {Stella Biderman and
Walter J. Scheirer},
title = {Pitfalls in Machine Learning Research: Reexamining the Development Cycle},
booktitle = {Proceedings of the I Can't Believe It's Not Better! Workshop
(ICBINB@NeurIPS 2020)},
year = {2020}
}

@InProceedings{MurrayWNGT19,
author = {Kenton Murray and
Jeff Kinnison and
Toan Nguyen and
Walter J. Scheirer and
David Chiang},
title = {Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance
for Low-Resource Machine Translation},
booktitle = {Workshop on Neural Generation and Translation (WNGT)},
year = {2019}
}

@article{BOYD2020483,
title = {Iris presentation attack detection: Where are we now?},
journal = {Pattern Recognition Letters},
volume = {138},
pages = {483-489},
year = {2020},
issn = {0167-8655},
doi = {https://doi.org/10.1016/j.patrec.2020.08.018},
url = {https://www.sciencedirect.com/science/article/pii/S0167865520303226},
author = {Aidan Boyd and Zhaoyuan Fang and Adam Czajka and Kevin W. Bowyer},
keywords = {Biometrics, Iris presentation attack detection, Security},
abstract = {As the popularity of iris recognition systems increases, the importance of effective security measures against presentation attacks becomes paramount. This work presents an overview of the most important advances in the area of iris presentation attack detection published in the recent two years. Newly-released, publicly-available datasets for development and evaluation of iris presentation attack detection are discussed. Recent literature can be seen to be broken into three categories: traditional “hand-crafted” feature extraction and classification, deep learning-based solutions, and hybrid approaches fusing both methodologies. Conclusions of modern approaches underscore the difficulty of this task. Finally, commentary on possible directions for future research is provided.}
}

@inproceedings{Dumford20_IJCB,
author = {Jacob Dumford and
Walter J. Scheirer},
title = {Backdooring Convolutional Neural Networks via Targeted Weight Perturbations},
booktitle = {Proceedings of the IAPR/IEEE International Joint Conference on Biometrics (IJCB)},
year = {2020}
}

@inproceedings{McCurrie20_IJCB,
author = {Mel McCurrie and
Hamish Nicholson and
Walter J. Scheirer and
Samuel E. Anthony},
title = {Modeling Score Distributions and Continuous Covariates:
A Bayesian Approach},
booktitle = {Proceedings of the IAPR/IEEE International Joint Conference on
Biometrics (IJCB)},
year = {2020}
}

@ARTICLE{9146139,

  author={Boyd, Aidan and Yadav, Shivangi and Swearingen, Thomas and Kuehlkamp, Andrey and Trokielewicz, Mateusz and Benjamin, Eric and Maciejewicz, Piotr and Chute, Dennis and Ross, Arun and Flynn, Patrick and Bowyer, Kevin and Czajka, Adam},
  journal={IEEE Access},
  title={Post-Mortem Iris Recognition—A Survey and Assessment of the State of the Art},
  year={2020},
  volume={8},
  number={},
  pages={136570-136593},
  doi={10.1109/ACCESS.2020.3011364}}

@article{scheirer2020pandemic,
title={A Pandemic of Bad Science},
author={Scheirer, Walter},
journal={Bulletin of the Atomic Scientists},
volume={76},
number={4},
month={July},
year={2020},
publisher={Taylor \& Francis}
}

@article{https://doi.org/10.1111/1556-4029.14488,
author = {Trokielewicz, Mateusz and Czajka, Adam and Maciejewicz, Piotr},
title = {Post-mortem Iris Decomposition and its Dynamics in Morgue Conditions},
journal = {Journal of Forensic Sciences},
volume = {65},
number = {5},
pages = {1530-1538},
keywords = {iris recognition, eye, decomposition, postmortem, biometrics},
doi = {https://doi.org/10.1111/1556-4029.14488},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/1556-4029.14488},
eprint = {https://onlinelibrary.wiley.com/doi/pdf/10.1111/1556-4029.14488},
abstract = {Abstract With increasing interest in employing iris biometrics as a forensic tool for identification by investigation authorities, there is a need for a thorough examination and understanding of postmortem decomposition processes that take place within the human eyeball, especially the iris. This can prove useful for fast and accurate matching of antemortem with postmortem data acquired at crime scenes or mass casualties, as well as for ensuring correct dispatching of bodies from the incident scene to a mortuary or funeral homes. Following these needs of forensic community, this paper offers an analysis of the coarse effects of eyeball decay done from a perspective of automatic iris recognition. We analyze postmortem iris images acquired for a subject with a very long postmortem observation time horizon (34 days), in both visible light and near-infrared light (860 nm), as the latter wavelength is used in commercial iris recognition systems. Conclusions and suggestions are provided that may aid forensic examiners in successfully utilizing iris patterns in postmortem identification of deceased subjects. Initial guidelines regarding the imaging process, types of illumination, and resolution are also given, together with expectations with respect to the iris features decomposition rates. Visible iris features possible for human, expert-based matching persists even up to 407 h postmortem, and near-infrared illumination is suggested for better mitigation of corneal opacity while imaging cadaver eyes (Post-mortem iris decomposition and its dynamics in morgue conditions. ArXiv pre-print, 2019).},
year = {2020}
}

@ARTICLE{9097964,

author={W. {Scheirer} and R. {VidalMata} and S. {Banerjee} and B. {RichardWebster} and M. {Albright} and P. {Davalos} and S. {McCloskey} and B. {Miller} and A. {Tambo} and S. {Ghosh} and S. {Nagesh} and Y. {Yuan} and Y. {Hu} and J. {Wu} and W. {Yang} and X. {Zhang} and J. {Liu} and Z. {Wang} and H. {Chen} and T. {Huang} and W. {Chin} and Y. {Li} and M. {Lababidi} and C. {Otto}},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Bridging the Gap Between Computational Photography and Visual Recognition},

year={2020},
volume={},
number={},
pages={1-1},}

@misc{agrawal2020generation,
title={The Next Generation of Human-Drone Partnerships: Co-Designing an Emergency
Response System},
author={Ankit Agrawal and Sophia Abraham and Benjamin Burger and Chichi Christine
and Luke Fraser and John Hoeksema and Sara Hwang and Elizabeth Travnik and
Shreya Kumar and Walter Scheirer and Jane Cleland-Huang and Michael Vierhauser
and Ryan Bauer and Steve Cox},
year={2020},
eprint={2001.03849},
archivePrefix={arXiv},
primaryClass={cs.HC}
}

@article{yang2020advancing,
title={Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study},
author={Yang, Wenhan and
Yuan, Ye and
Ren, Wenqi and
Liu, Jiaying and
Scheirer, Walter and
Wang, Zhangyang and
others},
journal={IEEE Transactions on Image Processing},
volume={29},
pages={5737--5752},
year={2020},
publisher={IEEE}
}

@ARTICLE{9001031, 

author={K. S. {Krishnapriya} and V. {Albiero} and K. {Vangara} and M. C. {King} and K. W. {Bowyer}}, 

journal={IEEE Transactions on Technology and Society}, 

title={Issues Related to Face Recognition Accuracy Varying Based on Race and Skin Tone},  

year={2020}, 

volume={1}, 

number={1}, 

pages={8-20},

}

@inproceedings{BanerjeeWACV2020,
author = {Sandipan Banerjee and
Walter J. Scheirer and
Kevin W. Bowyer and
Patrick J. Flynn},
title = {On Hallucinating Context and Background Pixels from a Face Mask using
Multi-scale GANs},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision
(WACV)},
year = {2020}
}

@article{yankoski2020ai,
title={An AI early warning system to monitor online disinformation, stop violence, and protect elections},
author={Yankoski, Michael and Weninger, Tim and Scheirer, Walter},
journal={Bulletin of the Atomic Scientists},
month={March},
year={2020},
publisher={Taylor \& Francis}
}

@article{MilfordPotentials2020,
author = {Michael Milford and
Samuel E. Anthony and
Walter J. Scheirer},
title = {Self-Driving Vehicles: Key Technical Challenges and Progress Off the Road},
journal = {IEEE Potentials},
volume = {39},
number = {1},
month = {January-February},
year = {2020}
}

@InProceedings{vidalmata2021joint,
title={Joint Visual-Temporal Embedding for Unsupervised Learning of Actions
in Untrimmed Sequences},
author={Rosaura G. VidalMata and Walter J. Scheirer and David D. Cox
and Anna Kukleva and Hilde Kuehne},
booktitle={IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
year={2021},
}

@InProceedings{Albiero_2020_WACV,
author = {Albiero, Vitor and K.S., Krishnapriya and Vangara, Kushal and Zhang, Kai and King, Michael C. and Bowyer, Kevin W.},
title = {Analysis of Gender Inequality In Face Recognition Accuracy},
booktitle = {The IEEE Winter Conference on Applications of Computer Vision (WACV) Workshops},
month = {March},
year = {2020}
}

@misc{bharati2020learning,
title={Learning Transformation-Aware Embeddings for Image Forensics},
author={Aparna Bharati and Daniel Moreira and Patrick Flynn and
Anderson Rocha and Kevin Bowyer and Walter Scheirer},
year={2020},
eprint={2001.04547},
archivePrefix={arXiv},
primaryClass={cs.CV}
}

@InProceedings{Albiero_2020_WACV,
author = {Albiero, Vitor and Bowyer, Kevin and Vangara, Kushal and King, Michael},
title = {Does Face Recognition Accuracy Get Better With Age? Deep Face Matchers Say No},
booktitle = {The IEEE Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}

@ARTICLE{8866753,

author={K. {Grm} and W. J. {Scheirer} and V. {Štruc}}, j

ournal={IEEE Transactions on Image Processing},

title={Face Hallucination Using Cascaded Super-Resolution and Identity Priors},

year={2020},

volume={29},

number={},

pages={2150-2165},

}

@ARTICLE{8818591,

author={A. {Czajka} and M. {Trokielewicz} and P. {Maciejewicz}},

journal={IEEE Spectrum},

title={The Eyes have it: New iris-recognition techniques can tell whether an Eye is healthy, diseased—or dead},

year={2019},

volume={56},

number={09},

pages={44-49},

}

@article{DBLP:journals/corr/abs-1805-11529,

  author    = {Pei Li and

               Loreto Prieto and

               Domingo Mery and

               Patrick J. Flynn},

  title     = {Low Resolution Face Recognition in the Wild},

  journal   = {CoRR},

  volume    = {abs/1805.11529},

  year      = {2018},

  url       = {http://arxiv.org/abs/1805.11529},

  archivePrefix = {arXiv},

  eprint    = {1805.11529},

  timestamp = {Wed, 06 Jun 2018 14:48:18 +0200},

  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1805-11529},

  bibsource = {dblp computer science bibliography, https://dblp.org}

}

@ARTICLE{8457272,

author={J. {Thompson} and P. {Flynn} and C. {Boehnen} and H. {Santos-Villalobos}},

journal={IEEE Transactions on Information Forensics and Security},

title={Assessing the Impact of Corneal Refraction and Iris Tissue Non-Planarity on Iris Recognition},

year={2019},

volume={14},

number={8},

pages={2102-2112},

}

@INPROCEEDINGS{8987377,

author={J. {Kinnison} and M. {Trokielewicz} and C. {Carballo} and A. {Czajka} and W. {Scheirer}},

booktitle={2019 International Conference on Biometrics (ICB)},

title={Learning-Free Iris Segmentation Revisited: A First Step Toward Fast Volumetric Operation Over Video Samples},

year={2019},

volume={},

number={},

pages={1-8},

}

@INPROCEEDINGS{8987299,

author={D. {Kerrigan} and M. {Trokielewicz} and A. {Czajka} and K. W. {Bowyer}},

booktitle={2019 International Conference on Biometrics (ICB)},

title={Iris Recognition with Image Segmentation Employing Retrained Off-the-Shelf Deep Neural Networks},

year={2019},

volume={},

number={},

pages={1-7},

}

@article{DBLP:journals/corr/abs-1812-09010,
author = {Klemen Grm and
Martin Pernus and
Leo Cluzel and
Walter J. Scheirer and
Simon Dobrisek and
Vitomir Struc},
title = {Face Hallucination Revisited: An Exploratory Study on Dataset Bias},
journal = {CoRR},
volume = {abs/1812.09010},
year = {2018},
url = {http://arxiv.org/abs/1812.09010},
archivePrefix = {arXiv},
eprint = {1812.09010},
timestamp = {Wed, 02 Jan 2019 14:40:18 +0100},
biburl = {https://dblp.org/rec/bib/journals/corr/abs-1812-09010},
bibsource = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{Tornai,
author = {Kalman Tornai and
Walter J. Scheirer},
title = {Gesture-based User Identity Verification as an Open Set Problem for Smartphones},
booktitle = {IAPR International Conference On Biometrics},
year = {2019},
}

@ARTICLE{8710265,

author={D. P. {Benalcazar} and D. {Bastias} and C. A. {Perez} and K. W. {Bowyer}},

journal={IEEE Access},

title={A 3D Iris Scanner From Multiple 2D Visible Light Images},

year={2019},

volume={7},

number={},

pages={61461-61472},

}

@INPROCEEDINGS{8759448,

author={S. {Mishra} and P. {Liang} and A. {Czajka} and D. Z. {Chen} and X. S. {Hu}},

booktitle={2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)},

title={CC-NET: Image Complexity Guided Network Compression for Biomedical Image Segmentation},

year={2019},

volume={},

number={},

pages={57-60},

}

@ARTICLE{10.3389/fncom.2019.00003,
AUTHOR={Banerjee, Sreya and Scheirer, Walter J. and Li, Lei},   
TITLE={An Extreme Value Theory Model of Cross-Modal Sensory Information Integration in Modulation of Vertebrate Visual System Functions},      
JOURNAL={Frontiers in Computational Neuroscience},      
VOLUME={13},      
PAGES={3},     
YEAR={2019},
URL={https://www.frontiersin.org/article/10.3389/fncom.2019.00003},       
DOI={10.3389/fncom.2019.00003},      
ISSN={1662-5188},   
}

@INPROCEEDINGS{8658792,

author={S. {Banerjee} and W. J. {Scheirer} and K. W. {Bowyer} and P. J. {Flynn}},

booktitle={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},

title={Fast Face Image Synthesis With Minimal Training},

year={2019},

volume={},

number={},

pages={2126-2136},}

@INPROCEEDINGS{8659059,

author={D. {Benalcazar} and C. {Perez} and D. {Bastias} and K. {Bowyer}},

booktitle={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},

title={Iris Recognition: Comparing Visible-Light Lateral and Frontal Illumination to NIR Frontal Illumination},

year={2019},

volume={},

number={},

pages={867-876},

}

@INPROCEEDINGS{8658404,

author={A. {Bharati} and D. {Moreira} and J. {Brogan} and P. {Hale} and K. {Bowyer} and P. {Flynn} and A. {Rocha} and W. {Scheirer}},

booktitle={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},

title={Beyond Pixels: Image Provenance Analysis Leveraging Metadata},

year={2019},

volume={},

number={},

pages={1692-1702},

}

@INPROCEEDINGS{8658879,

author={A. {Czajka} and Z. {Fang} and K. {Bowyer}},

booktitle={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},

title={Iris Presentation Attack Detection Based on Photometric Stereo Features},

year={2019}, volume={},

number={},

pages={877-885},

}

@INPROCEEDINGS{8659186,

author={A. {Kuehlkamp} and K. {Bowyer}},

booktitle={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},

title={Predicting Gender From Iris Texture May Be Harder Than It Seems},

year={2019},

volume={},

number={},

pages={904-912},

}

@ARTICLE{8412174,

author={B. {Shen} and C. W. {Forstall} and A. D. R. {Rocha} and W. J. {Scheirer}},

journal={IEEE Access},

title={Practical Text Phylogeny for Real-World Settings},

year={2018},

volume={6},

number={},

pages={41002-41012},

}

@ARTICLE{8513867, 

author={A. {Kuehlkamp} and A. {Pinto} and A. {Rocha} and K. W. {Bowyer} and A. {Czajka}}, 

journal={IEEE Transactions on Information Forensics and Security}, 

title={Ensemble of Multi-View Learning Classifiers for Cross-Domain Iris Presentation Attack Detection},

year={2019}, 

volume={14}, 

number={6}, 

pages={1419-1431},

}

@InProceedings{Trokielewicz_BTAS_2018,

  author    = {Mateusz Trokielewicz and Adam Czajka and Piotr Maciejewicz},

  title     = {Recognition of Post-mortem Irises for Presentation Attack Detection},

  booktitle = {{IEEE} International Conference on Biometrics: Theory Applications and Systems (BTAS)},

  year      = {2018},

  pages     = {1-6},

  address   = {Los Angeles, CA, USA},

  month     = {October},

  publisher = {IEEE},

  abstract  = {This paper presents a deep-learning-based method for iris presentation attack detection (PAD) when iris images are obtained from deceased people. Post-mortem iris recognition, despite being a potentially useful method that could aid forensic identification, can also pose challenges when used inappropriately, i.e., by using a dead organ of a person in an unauthorized way. Our approach is based on the VGG-16 architecture fine-tuned with a database of 574 post-mortem, near-infrared iris images from the Warsaw-BioBase-PostMortem-Iris-v1 database, complemented by a dataset of 256 images of live irises, collected within the scope of this study. Experiments described in this paper show that our approach is able to correctly classify iris images as either representing a live or a dead eye in almost 99\% of the trials, averaged over 20 subject-disjoint, train/test splits. We also show that the post-mortem iris detection accuracy increases as time since death elapses, and that we are able to construct a classification system with APCER=0% @BPCER = 1% when only post-mortem samples collected at least 16 hours post-mortem are considered. Since acquisitions of ante- and post-mortem samples differ significantly, we applied countermeasures to minimize bias in our classification methodology caused by image properties that are not related to the PAD. This included using the same iris sensor in collection of ante- and post-mortem samples, and analysis of class activation mapping to ensure that the discriminant iris regions utilized by our classifier are related to properties of the eye, and not to the acquisition protocol. This paper offers the first known to us PAS method in a post-mortem setting, together with an explanation of the decisions made by the convolutional neural network. Along with the paper we offer source codes, weights of the trained network, and a dataset of live iris images to facilitate reproducibility and further research.},

  day       = {22-25},

}

@inproceedings{blanchard_getting_2018,

    address = {Melbourne, Australia},

    title = {Getting the subtext without the text: {Scalable} multimodal sentiment classification from visual and acoustic modalities},

    copyright = {All rights reserved},

    booktitle = {Proceedings of the 56th {Annual} {Meeting} of the {Association} for {Computational} {Linguistics} ({ACL} 2018) ({First} {Workshop} and {Grand} {Challenge} on {Computational} {Modeling} of {Human} {Multimodal} {Language})},

    publisher = {Association for Computational Linguistics},

    author = {Blanchard, Nathaniel and Moreira, Daniel and Bharati, Aparna and Scheirer, Walter J.},

    year = {2018}

}

@InCollection{Czajka_PAD_Handbook_2018,

  author    = {Adam Czajka and Benedict Becker},

  title     = {{Application of Dynamic Features of the Pupil for Iris Presentation Attack Detection}},

  booktitle = {Handbook of Biometric Anti-Spoofing (2nd Edition, to appear)},

  publisher = {Springer International Publishing AG},

  year      = {2018},

  editor    = {S\'{e}bastien Marcel and Mark Nixon and Julian Fierrez and Nicholas Evans},

  pages     = {1--17},

  abstract  = {This chapter presents a comprehensive study on application of stimulated pupillary light reflex to presentation attack detection (PAD) that can be used in iris recognition systems. A pupil, when stimulated by visible light in a predefined manner, may offer sophisticated dynamic liveness features that cannot be acquired from dead eyes or other static objects such as printed contact lenses, paper printouts or prosthetic eyes. Modeling of pupil dynamics requires a few seconds of observation under varying light conditions that can be supplied by a visible light source in addition to the existing near-infrared illuminants used in iris image acquisition. The central element of the presented approach is an accurate modeling and classification of pupil dynamics that makes mimicking an actual eye reaction difficult. This chapter discusses new data-driven models of pupil dynamics based on recurrent neural networks and compares their PAD performance to solutions based on parametric Clynes-Kohn model and various classification techniques. Experiments with 166 distinct eyes of 84 subjects show that the best data-driven solution, one based on long-short term memory, was able to correctly recognize 99.97\% of attack presentations and 98.62\% of normal pupil reactions. In the approach using the Clynes-Kohn parametric model of pupil dynamics, we were able to perfectly recognize abnormalities and correctly recognize 99.97\% of normal pupil reactions on the same dataset with the same evaluation protocol as the data-driven approach. This means that the data-driven solutions favorably compare to the parametric approaches, which require model identification in exchange for a slightly better performance. We also show that observation times may be as short as 3 seconds when using the parametric model, and as short as 2 seconds when applying the recurrent neural network without substantial loss in accuracy. Along with this chapter we also offer: a) all time series representing pupil dynamics for 166 distinct eyes used in this study, b) weights of the trained recurrent neural network offering the best performance, c) source codes of the reference PAD implementation based on Clynes-Kohn parametric model, and d) all PAD scores that allow the reproduction of the plots presented in this chapter. To our best knowledge, this chapter proposes the first database of pupil measurements dedicated to presentation attack detection and the first evaluation of recurrent neural network-based modeling of pupil dynamics and PAD.},

}

@Article{Czajka_CSUR_2018,

  author    = {Adam Czajka and Kevin W. Bowyer},

  title     = {Presentation Attack Detection for Iris Recognition: An Assessment of the State of the Art},

  journal   = {{ACM} Computing Surveys},

  year      = {2018},

  volume    = {1},

  number    = {1},

  pages     = {1--35},

  issn      = {0360-0300},

  note      = {in press},

  acmid     = {3232849},

  address   = {New York, NY, USA},

  doi       = {10.1145/3232849},

  numpages  = {35},

  publisher = {ACM},

  url       = {http://doi.acm.org/10.1145/3232849},

}

@InProceedings{Trokielewicz_IWBF_2018,

  author    = {Mateusz Trokielewicz and Adam Czajka},

  title     = {Data-Driven Segmentation of Post-mortem Iris Images},

  booktitle = {{IAPR/IEEE} International Conference on Biometrics and Forensics (IWBF)},

  year      = {2018},

  pages     = {1-6},

  address   = {Sassari, Italy},

  month     = {June},

  publisher = {IAPR/IEEE},

  abstract  = {This paper presents a method for segmenting iris images obtained from the deceased subjects, by training a deep convolutional neural network (DCNN) designed for the purpose of semantic segmentation. Post-mortem iris recognition has recently emerged as an alternative, or additional, method useful in forensic analysis. At the same time it poses many new challenges from the technological standpoint, one of them being the image segmentation stage, which has proven difficult to be reliably executed by conventional iris recognition methods. Our approach is based on the SegNet architecture, fine-tuned with 1,300 manually segmented post-mortem iris images taken from the Warsaw-BioBase-Post-Mortem-Iris v1.0 database. The experiments presented in this paper show that this data-driven solution is able to learn specific deformations present in post-mortem samples, which are missing from alive irises, and offers a considerable improvement over the state-of-the-art, conventional segmentation algorithm (OSIRIS): the Intersection over Union (IoU) metric was improved from 73.6% (for OSIRIS) to 83% (for DCNN-based presented in this paper) averaged over subject-disjoint, multiple splits of the data into train and test subsets. This paper offers the first known to us method of automatic processing of post-mortem iris images. We offer source codes with the trained DCNN that perform end-to-end segmentation of post-mortem iris images, as described in this paper. Also, we offer binary masks corresponding to manual segmentation of samples from Warsaw-BioBase-Post-Mortem-Iris v1.0 database to facilitate development of alternative methods for post-mortem iris segmentation.},

  day       = {7-8},

}

@article{DBLP:journals/corr/abs-1804-01962,

  author    = {Mateusz Trokielewicz and

               Adam Czajka and

               Piotr Maciejewicz},

  title     = {Iris Recognition After Death},

  journal   = {CoRR},

  volume    = {abs/1804.01962},

  year      = {2018},

  url       = {http://arxiv.org/abs/1804.01962},

  archivePrefix = {arXiv},

  eprint    = {1804.01962},

  timestamp = {Tue, 01 May 2018 19:46:29 +0200},

  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1804-01962},

  bibsource = {dblp computer science bibliography, https://dblp.org}

}

@InProceedings{Bartuzi_IWBF_2018,

  author    = {Ewelina Bartuzi and Katarzyna Roszczewska and Andrzej Pacut and Adam Czajka},

  title     = {Unconstrained Biometric Recognition based on Thermal Hand Images},

  booktitle = {{IAPR/IEEE} International Conference on Biometrics and Forensics (IWBF)},

  year      = {2018},

  pages     = {1-6},

  address   = {Sassari, Italy},

  month     = {June},

  publisher = {IAPR/IEEE},

  abstract  = {This paper proposes a biometric recognition method based on thermal images of inner part of the hand, and a database of 21,000 thermal images of both hands acquired by a specialized thermal camera from 70 subjects. The data for each subject was acquired in three different sessions, with two first sessions organized on the same day, and the third session organized approximately two weeks apart. This allowed to analyze the stability of hand temperature in both short-term and long-term horizons. No hand stabilization or positioning devices were used during acquisition, making this setup closer to real-world, unconstrained applications. This required mak- ing our method translation-, rotation- and scale-invariant. Two approaches for feature selection and classification are proposed and compared: feature engineering deploying texture descriptors such as Binarized Statistical Image Features (BSIF) and Gabor wavelets, and feature learning based on convolutional neural networks (CNN) trained in different environmental conditions. For within-session scenario we achieved 0.36% and 0.00% of equal error rate (EER) in the first and the second approach, respectively. Between-session EER stands at 27.98% for the first approach and 17.17% for the second one. These results allow for estimation of a short-term stability of hand thermal information. This paper presents the first known to us database of hand thermal images and the first biometric system based solely on hand thermal maps acquired by thermal sensor in unconstrained scenario.},

  day       = {7-8},

}

@article{Sunderhauf2018,
author = {Niko Sunderhauf and
Oliver Brock and
Walter J. Scheirer and
Raia Hadsell and
Dieter Fox and
Jurgen Leitner and
Ben Upcroft and
Pieter Abbeel and
Wolfram Burgard and
Michael Milford and
Peter Corke},
title = {The Limits and Potentials of Deep Learning for Robotics},
journal = {International Journal of Robotics Research},
volume = {37},
number = {4-5},
year = {2018}
}

@article{KUEHLKAMP201817,

title = "Found a good match: Should I keep searching? — Accuracy and performance in iris matching using 1-to-First search",

journal = "Image and Vision Computing",

volume = "73",

pages = "17 - 27",

year = "2018",

issn = "0262-8856",

doi = "https://doi.org/10.1016/j.imavis.2018.03.003",

url = "http://www.sciencedirect.com/science/article/pii/S026288561830026X",

author = "Andrey Kuehlkamp and Kevin Bowyer",

keywords = "Biometrics, Iris recognition, Error rates, Identification, Accuracy, Search, 1:First, 1:N, Open-set"

}

@InProceedings{Banerjee_2017_IJCB,
author = {Sandipan Banerjee and Joel Brogan and Aparna Bharati and
Brandon RichardWebster and Vitomir Struc and Patrick Flynn
and Walter J. Scheirer},
title = {To Frontalize or Not to Frontalize: Do We Really Need Elaborate Pre-processing to Improve Face Recognition?},
booktitle = {The IEEE Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2018}
}

@InProceedings{vidal2018ug,
title={UG$^{2}$: a Video Benchmark for Assessing the Impact of Image Restoration and Enhancement on Automatic Visual Recognition},
author={Vidal, Rosaura G and Banerjee, Sreya and Grm, Klemen and Struc, Vitomir and Scheirer, Walter J},
booktitle={IEEE Winter Conference on Applications of Computer Vision (WACV)},
year={2018}
}

@InProceedings{KinnisonKTS17,
author = {Jeff Kinnison and
Nathaniel Kremer{-}Herman and
Douglas Thain and
Walter J. Scheirer},
title = {{SHADHO:} Massively Scalable Hardware-Aware Distributed Hyperparameter
Optimization},
booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
year = {2018}
}

@inProceedings{MetoyerA18,
author = {Ronald Metoyer and
Qiyu Zhi and
Bart Janczuk and
Walter J. Scheirer},
title = {Coupling Story to Visualization: Using Textual Analysis as a Bridge Between Data and Interpretation},
booktitle = {ACM International Conference on Intelligent User Interfaces (IUI)},
year = {2018}
}

@article{Rudd_2018_TPAMI,
author = {Ethan Rudd and Lalit P. Jain and Walter J. Scheirer and Terrance Boult},
title = {The Extreme Value Machine},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)},
volume = {40},
number = {3},
month = {March},
year = {2018}
}

@article{fong2018using,
title={Using human brain activity to guide machine learning},
author={Fong, Ruth C and Scheirer, Walter J and Cox, David D},
journal={Scientific reports},
volume={8},
number={1},
pages={5397},
year={2018},
publisher={Nature Publishing Group}
}

@InCollection{Pinto_DLB_2018,

  pages     = {245--293},

  address   = {Boca Raton, London, New York},

  title     = {Counteracting Presentation Attacks in Face, Fingerprint, and Iris Recognition},

  publisher = {CRC Press},

  year      = {2018},

  author    = {Allan Pinto and Helio Pedrini and Michael Krumdick and Benedict Becker and Adam Czajka and Kevin W. Bowyer and Anderson Rocha},

  editor    = {Mayank Vatsa, Richa Singh, Angshul Majumdar},

  isbn      = {9781138578234},

  booktitle = {Deep Learning in Biometrics},

  url       = {https://www.crcpress.com/Deep-Learning-in-Biometrics/Vatsa-Singh-Majumdar/p/book/9781138578234},

}

@article{DBLP:journals/corr/abs-1801-06510,

  author    = {Daniel Moreira and

               Aparna Bharati and

               Joel Brogan and

               Allan da Silva Pinto and

               Michael Parowski and

               Kevin W. Bowyer and

               Patrick J. Flynn and

               Anderson Rocha and

               Walter J. Scheirer},

  title     = {Image Provenance Analysis at Scale},

  journal   = {CoRR},

  volume    = {abs/1801.06510},

  year      = {2018},

  url       = {http://arxiv.org/abs/1801.06510},

  archivePrefix = {arXiv},

  eprint    = {1801.06510},

  timestamp = {Fri, 02 Feb 2018 14:20:25 +0100},

  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1801-06510},

  bibsource = {dblp computer science bibliography, https://dblp.org}

}

@InProceedings{Banerjee_2017_IJCB,
author = {Sandipan Banerjee and John S. Bernhard and Walter J. Scheirer and Kevin Bowyer and Patrick Flynn},
title = {SREFI: Synthesis of Realistic Example Face Images},
booktitle = {The IAPR/IEEE International Joint Conference on Biometrics (IJCB)},
month = {October},
year = {2017}
}

@InProceedings{Yambay_IJCB_2017,

  author    = {David Yambay and Benedict Becker and Naman Kohli and Daksha Yadav and Adam Czajka and Kevin W. Bowyer and Stephanie Schuckers and Richa Singh and Mayank Vatsa and Afzel Noore and Diego Gragnaniello and C. Sansone and L. Verdoliva and Lingxiao He and Yiwei Ru and Haiqing Li and Nianfeng Liu and Zhenan Sun and Tieniu Tan},

  publisher = {IEEE},

  address   = {Denver, CO, USA},

  title     = {{LivDet Iris 2017} -- Iris Liveness Detection Competition 2017},

  booktitle = {{IEEE} International Joint Conference on Biometrics (IJCB)},

  year      = {2017},

  pages     = {1-6},

  abstract  = {Presentation attacks such as using a contact lens with a printed pattern or printouts of an iris can be utilized to bypass a biometric security system. Solutions which have been proposed to counteract this vulnerability are called Presentation Attack Detection (also commonly called live- ness detection or anti-spoofing) and detect the presence of such attacks. The first international iris liveness competi- tion was launched in 2013 in order to assess the perfor- mance of currently available PAD algorithms with a second competition in 2015. This paper presents detailed results of its third edition, LivDet-Iris 2017. Three software-based approaches to Presentation Attack Detection were submit- ted. Four datasets of live and spoof images were tested with an additional cross-sensor test. New datasets and novel sit- uations of data have resulted in this competition being of a higher difficulty than previous competitions. Anonymous received the best results with a rate of rejected live samples of 3.36% and rate of accepted spoof samples of 14.71%. The results show that even with advances, print-out iris attacks as well as patterned contacts lenses are still difficult for software-based systems to detect. Printed iris images were easier to be differentiated from live images in compar- ison to patterned contact lenses as was also seen in previous competitions.},

}

@INPROCEEDINGS{8272732, 

author={A. Bharati and M. Vatsa and R. Singh and K. W. Bowyer and X. Tong}, 

booktitle={2017 IEEE International Joint Conference on Biometrics (IJCB)}, 

title={Demography-based facial retouching detection using subclass supervised sparse autoencoder}, 

year={2017}, 

volume={}, 

number={}, 

pages={474-482}, 

keywords={demography;face recognition;feature extraction;image classification;image coding;image denoising;image representation;learning (artificial intelligence);MultiDemographic Retouched Faces dataset;demography;digital retouching;face image;facial retouching detection;generalized retouching detection;retouched images;retouching software packages;semisupervised autoencoder;sparse autoencoder;testing images;training;Databases;Face;Feature extraction;Shape;Skin;Support vector machines;Tools}, 

doi={10.1109/BTAS.2017.8272732}, 

ISSN={}, 

month={Oct},}

@INPROCEEDINGS{8122802, 

author={R. Liu and L. O. Hall and K. W. Bowyer and D. B. Goldgof and R. Gatenby and K. Ben Ahmed}, 

booktitle={2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC)}, 

title={Synthetic minority image over-sampling technique: How to improve AUC for glioblastoma patient survival prediction}, 

year={2017}, 

volume={}, 

number={}, 

pages={1357-1362}, 

keywords={Gaussian noise;diseases;feature extraction;image classification;image denoising;learning (artificial intelligence);medical image processing;sampling methods;tumours;AUC;Glioblastoma patient survival group prediction;Synthetic minority image over-sampling;feature vector level;glioblastoma patient survival prediction;histogram feature extraction;image level;medical data;medical images;minority class predictive accuracy;over-sampling minority class;synthetic feature vectors;synthetic minority class;uniform local binary patterns;Cancer;Feature extraction;Gaussian noise;Histograms;Predictive models;Tumors}, 

doi={10.1109/SMC.2017.8122802}, 

ISSN={}, 

month={Oct},}

@INPROCEEDINGS{8272735, 

author={D. Bastias and C. A. Perez and D. P. Benalcazar and K. W. Bowyer}, 

booktitle={2017 IEEE International Joint Conference on Biometrics (IJCB)}, 

title={A method for 3D iris reconstruction from multiple 2D near-infrared images}, 

year={2017}, 

volume={}, 

number={}, 

pages={503-509}, 

keywords={biometrics (access control);eye;feature extraction;image matching;image recognition;image reconstruction;image segmentation;image texture;infrared imaging;iris recognition;3D iris reconstruction;biometric identification;depth information;infrared iris images;iris enhancement;iris image acquisition;iris recognition;iris surface;iris texture equalization;occlusions;reliable current technique;reliable identification;Cameras;Iris;Iris recognition;Lighting;Solid modeling;Three-dimensional displays;Two dimensional displays}, 

doi={10.1109/BTAS.2017.8272735}, 

ISSN={}, 

month={Oct},}

@InProceedings{Brogan_2017_ICIP,
author = {Joel Brogan and
Paolo Bestagini and
Aparna Bharati and
Allan da Silva Pinto and
Daniel Moreira and
Kevin W. Bowyer and
Patrick J. Flynn and
Anderson Rocha and
Walter J. Scheirer},
title = {Spotting the Difference: Context Retrieval and Analysis for Improved
Forgery Detection and Localization},
booktitle = {IEEE International Conference on Image Processing (ICIP)},
year = {2017}
}

@InProceedings{Bharati_2017_ICIP,
author = {Aparna Bharati and
Daniel Moreira and
Allan da Silva Pinto and
Joel Brogan and
Kevin W. Bowyer and
Patrick J. Flynn and
Walter J. Scheirer and
Anderson Rocha},
title = {U-Phylogeny: Undirected Provenance Graph Consruction in the Wild},
booktitle = {IEEE International Conference on Image Processing (ICIP)},
year = {2017}
}

@InProceedings{Pinto_2017_ICIP,
author = {Allan da Silva Pinto and
Daniel Moreira and
Aparna Bharati and
Joel Brogan and
Kevin W. Bowyer and
Patrick J. Flynn and
Walter J. Scheirer and
Anderson Rocha},
title = {Provenance Filtering for Multimedia Phylogeny},
booktitle = {IEEE International Conference on Image Processing (ICIP)},
year = {2017}
}

@InProceedings{Chen_2017_MICCAI,
author = {Jianxu Chen and Sreya Banerjee and Abhinav Grama and Walter J. Scheirer and Danny Z. Chen},
title = {Neuron Segmentation Using Deep Complete Bipartite Networks},
booktitle = {International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)},
month = {September},
year = {2017}
}

@InProceedings{Jacobson_2017_IROS,
author = {Adam Jacobson and Walter J. Scheirer and Michael Milford},
title = {Deja vu: Scalable Place Recognition Using Mutually Supportive Feature Frequencies},
booktitle = {Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
month = {September},
year = {2017}
}

@Article{Czajka_TIFS_2017,

  author    = {Adam Czajka and Kevin W. Bowyer and Michael Krumdick and Rosaura G. VidalMata},

  title     = {Recognition of Image-Orientation-Based Iris Spoofing},

  journal   = {{IEEE} Transactions on Information Forensics and Security},

  year      = {2017},

  volume    = {12},

  number    = {9},

  pages     = {2184-2196},

  month     = {September},

  issn      = {1556-6013},

  abstract  = {This paper presents a solution to automatically recognize the correct left/right and upright/upside-down orientation of iris images. This solution can be used to counter spoofing attacks directed to generate fake identities by rotating an iris image or the iris sensor during the acquisition. Two approaches are compared on the same data, using the same evaluation protocol: 1) feature engineering, using hand-crafted features classified by a support vector machine (SVM) and 2) feature learning, using data-driven features learned and classified by a convolutional neural network (CNN). A data set of 20 750 iris images, acquired for 103 subjects using four sensors, was used for development. An additional subject-disjoint data set of 1,939 images, from 32 additional subjects, was used for testing purposes. Both same-sensor and cross-sensor tests were carried out to investigate how the classification approaches generalize to unknown hardware. The SVM-based approach achieved an average correct classification rate above 95% (89%) for recognition of left/right (upright/upside-down) orientation when tested on subject-disjoint data and camera-disjoint data, and 99% (97%) if the images were acquired by the same sensor. The CNN-based approach performed better for same-sensor experiments, and presented slightly worse generalization capabilities to unknown sensors when compared with the SVM. We are not aware of any other papers on the automatic recognition of upright/upside-down orientation of iris images, or studying both hand-crafted and data-driven features in same-sensor and cross-sensor subject-disjoint experiments. The data sets used in this paper, along with random splits of the data used in cross-validation, are being made available.},

  doi       = {10.1109/TIFS.2017.2701332},

  keywords  = {cameras;feature extraction;image classification;image sensors;iris recognition;learning (artificial intelligence);support vector machines;CNN-based approach;SVM-based approach;camera-disjoint data;classification approaches;convolutional neural network;cross-sensor subject-disjoint experiments;cross-sensor tests;data-driven feature learning;feature engineering;image-orientation-based iris spoofing recognition;iris image left/right orientation;iris image upright/upside-down orientation;iris sensor;same-sensor subject-disjoint experiments;same-sensor tests;spoofing attacks;subject-disjoint data;support vector machine;Ducts;Head;Image recognition;Iris;Iris recognition;Neural networks;Support vector machines;Iris recognition;presentation attack detection;spoofing},

  publisher = {IEEE},

}

@Article{Czajka_IET_2017,

  author    = {Adam Czajka and Kevin W. Bowyer and Estefan Ortiz},

  title     = {Analysis of diurnal changes in pupil dilation and eyelid aperture},

  journal   = {IET Biometrics},

  year      = {2018},

  volume    = {7},

  pages     = {136-144(8)},

  month     = {March},

  issn      = {2047-4938},

  abstract  = {This work is inspired by the observation of surprising daily fluctuations in the number of valid iris code bits used to match irises in the NEXUS program operated by the Canadian Border Security Agency. These fluctuations have an impact on iris comparison scores but cannot be simply explained by pupil dilation, which does not have a clear pattern that would generalise to a population. To check if fluctuations in the number of valid iris code bits may be explained by eyelid aperture observed in a controlled, laboratory environment, the eyelid aperture was measured for 18 subjects participating in an acquisition every 2 h during the day. Simultaneously, the pupil dilation was measured to check the existence of a daily pattern for a population and for single subjects. There are two interesting outcomes of this work. First, there are statistically significant changes during the day in both pupil dilation and eyelid opening observed for individual subjects. Second, these changes do not generalise well into a common pattern for the group. Consequently, the diurnal fluctuations in the number of bits compared and the comparison score observed in the NEXUS program cannot be explained by changes in pupil dilation nor by eyelid aperture.},

  copyright = {© The Institution of Engineering and Technology},

  issue     = {2},

  keywords  = {pupil dilation;diurnal fluctuations;iris matching;eyelid aperture;NEXUS program;valid iris code bit daily fluctuations;Canadian Border Security Agency;iris comparison scores;diurnal change analysis;},

  language  = {English},

  publisher = {Institution of Engineering and Technology},

  url       = {http://digital-library.theiet.org/content/journals/10.1049/iet-bmt.2016.0191},

}

@ARTICLE{7875165, 

author={T. Larrain and J. S. Bernhard and D. Mery and K. W. Bowyer}, 

journal={IEEE Transactions on Information Forensics and Security}, 

title={Face Recognition Using Sparse Fingerprint Classification Algorithm}, 

year={2017}, 

volume={12}, 

number={7}, 

pages={1646-1657}, 

keywords={face recognition;fingerprint identification;image classification;image representation;query processing;SFCA;dictionary;face recognition;query image;sparse fingerprint classification algorithm;sparse representation;Dictionaries;Face;Face recognition;Feature extraction;Fingerprint recognition;Lighting;Training;Face recognition}, 

doi={10.1109/TIFS.2017.2680403}, 

ISSN={1556-6013}, 

month={July},}

@INPROCEEDINGS{7926716,

author={A. Kuehlkamp and B. Becker and K. Bowyer},

booktitle={2017 IEEE Winter Conference on Applications of Computer Vision (WACV)},

title={Gender-from-Iris or Gender-from-Mascara?},

year={2017},

volume={},

number={},

pages={1151-1159},

keywords={feedforward neural nets;image classification;image segmentation;image texture;multilayer perceptrons;classifiers;convolutional neural networks;cosmetics effect;data-driven features;eyelash occlusion;gender-from-iris problem;gender-from-iris texture;hand-crafted features;multilayer perceptron;person-disjoint train;segmentation;Feature extraction;Image segmentation;Iris;Iris recognition;Support vector machines;Testing;Training},

doi={10.1109/WACV.2017.133},

ISSN={},

month={March},

}

@article{Grant:2017:CSU:3058792.3052930,

 author = {Grant, Jason M. and Flynn, Patrick J.},

 title = {Crowd Scene Understanding from Video: A Survey},

 journal = {ACM Trans. Multimedia Comput. Commun. Appl.},

 issue_date = {May 2017},

 volume = {13},

 number = {2},

 month = mar,

 year = {2017},

 issn = {1551-6857},

 pages = {19:1--19:23},

 articleno = {19},

 numpages = {23},

 url = {http://doi.acm.org/10.1145/3052930},

 doi = {10.1145/3052930},

 acmid = {3052930},

 publisher = {ACM},

 address = {New York, NY, USA},

 keywords = {Crowd analysis, datasets, human activity},

} 

@InProceedings{McCurie_2017_FG,
author = {Mel McCurie and Fernando Beletti and Lucas Parzianello and Allen Westendorp and
Samuel E. Anthony and Walter J. Scheirer},
title = {Predicting First Impressions with Deep Learning},
booktitle = {IEEE Conference on Automatic Face and Gesture Recognition (FG)},
month = {May},
year = {2017}
}

@article{DBLP:journals/corr/BanerjeeSSL17,
author = {Sandipan Banerjee and
James Sweet and
Christopher Sweet and
Marya Lieberman},
title = {Visual Recognition of Paper Analytical Device Images for Detection
of Falsified Pharmaceuticals},
journal = {CoRR},
volume = {abs/1704.04251},
year = {2017},
url = {http://arxiv.org/abs/1704.04251},
archivePrefix = {arXiv},
eprint = {1704.04251},
timestamp = {Wed, 07 Jun 2017 14:43:14 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/BanerjeeSSL17},
bibsource = {dblp computer science bibliography, https://dblp.org}
}

@ARTICLE{7775025, 

author={D. Mery and E. Svec and M. Arias and V. Riffo and J. M. Saavedra and S. Banerjee}, 

journal={IEEE Transactions on Systems, Man, and Cybernetics: Systems}, 

title={Modern Computer Vision Techniques for X-Ray Testing in Baggage Inspection}, 

year={2017}, 

volume={47}, 

number={4}, 

pages={682-692}, 

keywords={X-ray imaging;authorisation;automatic optical inspection;bags;computer vision;object recognition;GDXray database;X-ray screening systems;X-ray testing;access control;automated recognition;bag of words;baggage inspection;computer vision;deep features;deep learning;human inspection task;object recognition;pattern recognition;security checkpoints;sparse representations;visual vocabularies;Computer vision;Image recognition;Inspection;Object recognition;Testing;Weapons;X-ray imaging;Baggage screening;X-ray testing;deep learning;implicit shape model (ISM);object categorization;object detection;object recognition;sparse representations;threat objects}, 

doi={10.1109/TSMC.2016.2628381}, 

ISSN={2168-2216}, 

month={April},

}

@Conference{Trokielewicz_BIOSIGNALS_2017,

  author       = {Mateusz Trokielewicz and Adam Czajka and Piotr Maciejewicz},

  title        = {{Iris Recognition under Biologically Troublesome Conditions -- Effects of Aging, Diseases and Post-mortem Changes}},

  booktitle    = {Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies -- Volume 4: BIOSIGNALS, (BIOSTEC 2017)},

  year         = {2017},

  pages        = {253-258},

  organization = {INSTICC},

  publisher    = {SciTePress},

  abstract     = {This paper presents the most comprehensive analysis of iris recognition reliability in the occurrence of various biological processes happening naturally and pathologically in the human body, including aging, illnesses, and post-mortem changes to date. Insightful conclusions are offered in relation to all three of these aspects. Extensive regression analysis of the template aging phenomenon shows that differences in pupil dilation, combined with certain quality factors of the sample image and the progression of time itself can significantly degrade recognition accuracy. Impactful effects can also be observed when iris recognition is employed with eyes affected by certain eye pathologies or (even more) with eyes of the deceased subjects. Notably, appropriate databases are delivered to the biometric community to stimulate further research in these utterly important areas of iris biometrics studies. Finally, some open questions are stated to inspire further discussions and research on th ese important topics. To Authors’ best knowledge, this is the only scientific study of iris recognition reliability of such a broad scope and novelty.},

  doi          = {10.5220/0006251702530258},

  isbn         = {978-989-758-212-7},

}

@book{Scheirer_2017_MC,
author = {Walter J. Scheirer},
title = {Extreme Value Theory-Based Methods for Visual Recognition},
publisher = {Morgan & Claypool Publishers},
month = {February},
year = {2017}
}

@article{PHILLIPS201796,

title = "Lessons from collecting a million biometric samples",

journal = "Image and Vision Computing",

volume = "58",

pages = "96 - 107",

year = "2017",

issn = "0262-8856",

doi = "https://doi.org/10.1016/j.imavis.2016.08.004",

url = "http://www.sciencedirect.com/science/article/pii/S0262885616301287",

author = "P. Jonathon Phillips and Patrick J. Flynn and Kevin W. Bowyer",

keywords = "Face recognition, Algorithm performance, Human performance, Challenge problem"

}

@article{Scheirer_2017_TIFS,
author = {Anderson Rocha and Walter J. Scheirer and Thiago Cavalcante and Antonio Theophilo
and Bingyu Shen and Ariadne R. B. Carvalho and Efstathios Stamatatos},
title = {Authorship Attribution for Social Media Forensics},
journal = {IEEE Transactions on Information Forensics and Security (T-IFS)},
volume = {12},
issue = {1},
month = {January},
year = {2017}
}

@article{Tistarelli2017,

affiliation = {University of Sassari, Italy; Colorado State University, USA; University of Notre Dame, USA; University of Salerno, Italy},

author = {Tistarelli, Massimo and Beveridge, Ross and Flynn, Patrick and Nappi, Michele},

doi = {10.1016/j.imavis.2017.01.008},

journal = {Image and Vision Computing},

language = {English},

number = {Complete},

pages = {108-109},

title = {Guest Editors’ Introduction},

volume = {58},

year = {2017},

}

@INPROCEEDINGS{7791204, 

author={P. Li and J. Brogan and P. J. Flynn}, 

booktitle={2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS)}, 

title={Toward facial re-identification: Experiments with data from an operational surveillance camera plant}, 

year={2016}, 

volume={}, 

number={}, 

pages={1-8}, 

keywords={face recognition;feature extraction;image capture;image matching;image resolution;video surveillance;body ReID method;facial reidentification;facial resolution;low resolution facial features;municipal rapid transit system;operational surveillance camera plant;person reidentification;Bridges;Cameras;Feature extraction;Image color analysis;Image resolution;Neural networks;Principal component analysis}, 

doi={10.1109/BTAS.2016.7791204}, 

ISSN={}, 

month={Sept},

}

@book{bowyer2016handbook,

  title={Handbook of iris recognition},

  author={Bowyer, Kevin W and Burge, Mark J},

  year={2016},

  publisher={Springer}

}

@InProceedings{Trokielewicz_BTAS_2016,

  author    = {Mateusz Trokielewicz and Adam Czajka and Piotr Maciejewicz},

  title     = {Human iris recognition in post-mortem subjects: Study and database},

  booktitle = {{IEEE} International Conference on Biometrics: Theory Applications and Systems (BTAS)},

  publisher = {IEEE},

  address   = {Niagara Falls, NY, USA},

  year      = {2016},

  pages     = {1-6},

  month     = {Sept},

  abstract  = {This paper presents a unique study of post-mortem human iris recognition and the first known to us database of near-infrared and visible-light iris images of deceased humans collected up to almost 17 days after death. We used four different iris recognition methods to analyze the dynamics of iris quality decay in short-term comparisons (samples collected up to 60 hours after death) and long-term comparisons (for samples acquired up to 407 hours after demise). This study shows that post-mortem iris recognition is possible and occasionally works even 17 days after death. These conclusions contradict a promulgated rumor that iris is unusable shortly after decease. We make this dataset publicly available to let others verify our findings and to research new aspects of this important and unfamiliar topic. We are not aware of any earlier papers offering post-mortem human iris images and such comprehensive analysis employing four different matchers.},

  doi       = {10.1109/BTAS.2016.7791175},

  keywords  = {eye;iris recognition;deceased humans;iris quality decay;near-infrared iris images;post-mortem human iris recognition;time 17 day;time 407 h;time 60 h;visible-light iris images;Biomedical imaging;Cameras;Cornea;Databases;Iris recognition},

}

@InProceedings{Scheirer_2016_BTAS,
author = {Walter J. Scheirer and Patrick J. Flynn and Changxing Ding and Guodong Guo and Vitomir Struc and Mohamad Al Jazaery and Klemen Grm and Simon Dobrisek and Dacheng Tao and Yu Zhu and Joel Brogan and Sandipan Banerjee and Aparna Bharati and Brandon RichardWebster},
title = {Report on the BTAS 2016 Video Person Recognition Evaluation},
booktitle = {Proceedings of the IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS)},
year = {2016}
}

@INPROCEEDINGS{7791188, 

author={D. Mery and Y. Zhao and K. Bowyer}, 

booktitle={2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS)}, 

title={On accuracy estimation and comparison of results in biometric research}, 

year={2016}, 

volume={}, 

number={}, 

pages={1-8}, 

keywords={emotion recognition;face recognition;expression recognition;face recognition;gender classification;Databases;Estimation;Face;Face recognition;Protocols;Testing;Training}, 

doi={10.1109/BTAS.2016.7791188}, 

ISSN={}, 

month={Sept},}

@inproceedings{manjani2016template,

  title={Template aging in 3D and 2D face recognition},

  author={Manjani, Ishan and Sumerkan, Hakki and Flynn, Patrick J and Bowyer, Kevin W},

  booktitle={Biometrics Theory, Applications and Systems (BTAS), 2016 IEEE 8th International Conference on},

  pages={1--6},

  year={2016},

  organization={IEEE}

}

@INPROCEEDINGS{7791176, 

author={K. W. Bowyer and P. J. Flynn}, 

booktitle={2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS)}, 

title={Biometric identification of identical twins: A survey}, 

year={2016}, 

volume={}, 

number={}, 

pages={1-8}, 

keywords={biometrics (access control);security of data;biometric identification;biometric uncertainty;identical twins;DNA;Databases;Face;Face recognition;Fingerprint recognition;Fingers}, 

doi={10.1109/BTAS.2016.7791176}, 

ISSN={}, 

month={Sept},}

@INPROCEEDINGS{7791194, 

author={E. Ortiz and K. W. Bowyer}, 

booktitle={2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS)}, 

title={Pitfalls in studying #x201C;big data #x201D; from operational scenarios}, 

year={2016}, 

volume={}, 

number={}, 

pages={1-7}, 

keywords={Big Data;iris recognition;Big Data;NISTIREX VI report;operational biometric dataset;operational iris recognition dataset;operational scenarios;Aging;Airports;Big data;High definition video;Iris;Iris recognition;Probes}, 

doi={10.1109/BTAS.2016.7791194}, 

ISSN={}, 

month={Sept},}

@Article{Trokielewicz_IMAVIS_2017,

  author   = {Mateusz Trokielewicz and Adam Czajka and Piotr Maciejewicz},

  title    = {Implications of ocular pathologies for iris recognition reliability},

  journal  = {Image and Vision Computing},

  year     = {2017},

  volume   = {58},

  pages    = {158 - 167},

  issn     = {0262-8856},

  abstract = {This paper presents an analysis of how iris recognition is influenced by eye disease and an appropriate dataset comprising 2996 images of irises taken from 230 distinct eyes (including 184 affected by more than 20 different eye conditions). The images were collected in near infrared and visible light during routine ophthalmological examination. The experimental study carried out utilizing four independent iris recognition algorithms (MIRLIN, VeriEye, OSIRIS and IriCore) renders four valuable results. First, the enrollment process is highly sensitive to those eye conditions that obstruct the iris or cause geometrical distortions. Second, even those conditions that do not produce visible changes to the structure of the iris may increase the dissimilarity between samples of the same eyes. Third, eye conditions affecting the geometry or the tissue structure of the iris or otherwise producing obstructions significantly decrease same-eye similarity and have a lower, yet still statistically significant, influence on impostor comparison scores. Fourth, for unhealthy eyes, the most prominent effect of disease on iris recognition is to cause segmentation errors. To our knowledge this paper describes the largest database of iris images for disease-affected eyes made publicly available to researchers and offers the most comprehensive study of what we can expect when iris recognition is employed for diseased eyes.},

  doi      = {https://doi.org/10.1016/j.imavis.2016.08.001},

  keywords = {Iris recognition, Ocular disease, Biometrics, Ophthalmology},

  url      = {http://www.sciencedirect.com/science/article/pii/S0262885616301251},

}

@article{Joesch_2016_eLife,
author = {Joesch, Maximilian and Mankus, David and Yamagata, Masahito and Shahbazi, Ali and Schalek, Richard and
Suissa-Peleg, Adi and Meister, Markus and Lichtman, Jeff W. and Scheirer, Walter J. and Sanes, Joshua R.},
title = {Reconstruction of Genetically Identified Neurons Imaged by Serial-Section Electron Microscopy},
journal = {eLife},
volume = {5},
pages = {e15015},
year = {2016}
}

@article{chen2013iris,

  title={Iris Recognition Based on Human-Interpretable},

  author={Chen, Jianxu and Shen, Feng and Chen, Danny Z and Flynn, Patrick J},

  year={2013}

}

@ARTICLE{7422104, 

author={J. Chen and F. Shen and D. Z. Chen and P. J. Flynn}, 

journal={IEEE Transactions on Information Forensics and Security}, 

title={Iris Recognition Based on Human-Interpretable Features}, 

year={2016}, 

volume={11}, 

number={7}, 

pages={1476-1485}, 

keywords={iris recognition;human recognition;human-friendly techniques;human-in-the-loop iris recognition system;human-interpretable features;iris recognition;matching scheme;visible-feature-based iris recognition method;Algorithm design and analysis;Cryptography;Feature extraction;Forensics;Image segmentation;Iris recognition;Probes;Iris recognition;forensics;human-in-the-loop;iris recognition;visible feature}, 

doi={10.1109/TIFS.2016.2535901}, 

ISSN={1556-6013}, 

month={July},}

@InProceedings{Trokielewicz_ICB_2016,

  author    = {Mateusz Trokielewicz and Adam Czajka and Piotr Maciejewicz},

  title     = {Post-mortem human iris recognition},

  booktitle = {{IEEE} International Conference on Biometrics (ICB)},

  address   = {Halmstad, Sweden},

  publisher = {IEEE},

  year      = {2016},

  pages     = {1-6},

  month     = {June},

  abstract  = {This paper presents a unique analysis of post-mortem human iris recognition. Post-mortem human iris images were collected at the university mortuary in three sessions separated by approximately 11 hours, with the first session organized from 5 to 7 hours after demise. Analysis performed for four independent iris recognition methods shows that the common claim of the iris being useless for biometric identification soon after death is not entirely true. Since the pupil has a constant and neutral dilation after death (the so called “cadaveric position”), this makes the iris pattern perfectly visible from the standpoint of dilation. We found that more than 90% of irises are still correctly recognized when captured a few hours after death, and that serious iris deterioration begins approximately 22 hours later, since the recognition rate drops to a range of 13.3-73.3% (depending on the method used) when the cornea starts to be cloudy. There were only two failures to enroll (out of 104 images) observed for only a single method (out of four employed in this study). These findings show that the dynamics of post-mortem changes to the iris that are important for biometric identification are much more moderate than previously believed. To the best of our knowledge, this paper presents the first experimental study of how iris recognition works after death, and we hope that these preliminary findings will stimulate further research in this area.},

  doi       = {10.1109/ICB.2016.7550073},

  keywords  = {feature extraction;iris recognition;biometric identification;iris pattern;postmortem human iris recognition;Biomedical imaging;Cameras;Cornea;Degradation;Iris recognition;Pathology;Visualization},

}

@incollection{Czajka_Handbook_2016,

  pages     = {439--467},

  title     = {Iris Liveness Detection by Modeling Dynamic Pupil Features},

  publisher = {Springer London},

  year      = {2016},

  author    = {Czajka, Adam},

  editor    = {Bowyer, Kevin W. and Burge, Mark J.},

  address   = {London},

  isbn      = {978-1-4471-6784-6},

  abstract  = {The objective of this chapter is to present how to employ pupil dynamics in eye liveness detection. A thorough review of current liveness detection methods is provided at the beginning of the chapter to make the scientific background and position this method within current state-of-the-art methodology. Pupil dynamics may serve as a component of a wider presentation attack detection in iris recognition systems, making them more secure. Due to a lack of public databases that would support this research, we have built our own iris capture device to register pupil size changes under visible light stimuli, and registered 204 observations for 26 subjects (52 different irides), each containing 750 iris images taken every 40 ms. Each measurement registers the spontaneous pupil oscillations and its reaction after a sudden increase and a sudden decrease of the intensity of visible light. The Kohn and Clynes pupil dynamics model is used to describe these changes; hence, we convert each observation into a point in a feature space defined by model parameters. To answer the question whether the eye is alive (that is, if it reacts to light changes as a human eye) or the presentation is suspicious (that is, if it reacts oddly or no reaction is observed), we use linear and nonlinear support vector machines to classify natural reaction and spontaneous oscillations, simultaneously investigating the goodness of fit to reject bad modeling. Our experiments show that this approach can achieve a perfect performance for the data we have collected; all normal reactions are correctly differentiated from spontaneous oscillations. We investigated three variants of modeling to find the simplest, yet still powerful configuration of the method, namely (1) observing the pupil reaction to both the positive and negative changes in the light intensity, (2) using only the pupil reaction to positive surge of the light intensity, and (3) employing only the pupil reaction when the light is suddenly turned off. Further investigation related to the shortest observation time required to model the pupil reaction led to the final conclusion that time periods not exceeding 3 s are adequate to offer a perfect performance (on this dataset).},

  booktitle = {Handbook of Iris Recognition},

  comment   = {iris:PAD:dynamic:active},

  doi       = {10.1007/978-1-4471-6784-6_19},

  url       = {http://dx.doi.org/10.1007/978-1-4471-6784-6_19},

}

@Article{Czajka_BPASTS_2016,

  author    = {Adam Czajka and W\lodzimierz Kasprzak and Artur Wilkowski},

  title     = {Verification of iris image authenticity using fragile watermarking},

  journal   = {Bulletin of the Polish Academy of Sciences Technical Sciences},

  year      = {2016},

  volume    = {64},

  pages     = {807-819},

  month     = {December},

  issn      = {2300-1917},

  abstract  = {This paper proposes and evaluates a watermarking-based approach to certify the authenticity of iris images when they are captured by a genuine equipment. In the proposed method, the iris images are secretly signed before being used in biometric processes, and the resulting signature is embedded into the JPEG carrier image in the DCT domain in a data-dependent way. Any alteration of the original (certified) image makes the signature no longer corresponding to this image and this change can be quickly identified at the receiver site. Hence, it is called fragile watermarking to differentiate this method from regular watermarking that should present some robustness against image alterations. There is no need to attach any auxiliary signature data, hence the existing, already standardized transmission channels and storage protocols may be used. The embedding procedure requires to remove some part of the original information. But, by using the BATH dataset comprising 32 000 iris images collected for 1 600 distinct eyes, we verify that the proposed alterations have no impact on iris recognition reliability, although statistically significant, small differences in genuine score distributions are observed when the watermark is embedded to both the enrollment and verification iris images. This is a unique evaluation of how the watermark embedding of digital signatures into the ISO CROPPED iris images (during the enrollment, verification or both) influences the reliability of a well-established, commercial iris recognition methodology. Without loss in generality, this approach is targeted to biometric-enabled ID documents that deploy iris data to authenticate the holder of the document.},

  day       = {23},

  doi       = {https://doi.org/10.1515/bpasts-2016-0090},

  issue     = {4},

  keywords  = {biometric data authentication; iris recognition; steganography; watermarking},

  language  = {English},

  publisher = {De Gruyter},

  url       = {https://doi.org/10.1515/bpasts-2016-0090},

}

@INPROCEEDINGS{7477687,

author={A. Kuehlkamp and K. W. Bowyer},

booktitle={2016 IEEE Winter Conference on Applications of Computer Vision (WACV)},

title={An analysis of 1-to-first matching in iris recognition},

year={2016},

volume={},

number={},

pages={1-8},

keywords={image matching;iris recognition;search problems;1-to-N search;1-to-first matching analysis;below-threshold match;false match error rate;identification mode;iris images;iris recognition systems;modified 1-to-first search;Computer science;Databases;Error analysis;Iris recognition;Probes;Robustness},

doi={10.1109/WACV.2016.7477687},

ISSN={},

month={March},

}

@ARTICLE{7464282, 
author={A. Bharati and R. Singh and M. Vatsa and K. W. Bowyer}, 
journal={IEEE Transactions on Information Forensics and Security}, 
title={Detecting Facial Retouching Using Supervised Deep Learning}, 
year={2016}, 
volume={11}, 
number={9}, 
pages={1903-1913}, 
keywords={Boltzmann machines;Web sites;face recognition;image matching;learning (artificial intelligence);visual databases;Boltzmann machine algorithm;automatic face recognition;detecting facial retouching;digital alterations;face images;identification cards;image databases;image matching;photo sharing Web sites;social media;supervised deep learning;unaltered gallery image;Classification algorithms;Databases;Face;Face recognition;Media;Probes;Skin;Image forensics;biometric spoofing;face image alteration;face image retouching;face recognition}, 
doi={10.1109/TIFS.2016.2561898}, 
ISSN={1556-6013}, 
month={Sept},

}

@ARTICLE{7447785, 

author={J. E. Tapia and C. A. Perez and K. W. Bowyer}, 

journal={IEEE Transactions on Information Forensics and Security}, 

title={Gender Classification From the Same Iris Code Used for Recognition}, 

year={2016}, 

volume={11}, 

number={8}, 

pages={1760-1770}, 

keywords={feature selection;image classification;image texture;iris recognition;binary iris code;feature selection;gender classification;gender prediction;iris code;iris recognition;iris region;iris texture features;Feature extraction;Image segmentation;Iris;Iris recognition;Mutual information;Testing;Training;Feature Selection;Gender Classification;Gender classification;Iris;feature selection;iris}, 

doi={10.1109/TIFS.2016.2550418}, 

ISSN={1556-6013}, 

month={Aug},}

@article{Scheirer_2016_LLC,
author = {Walter J. Scheirer and Christopher W. Forstall and Neil Coffee},
title = {The Sense of a Connection: Automatic Tracing of Intertextuality by Meaning},
journal = {Literary and Linguistic Computing (LLC)},
volume = {31},
issue = {1},
month = {April},
year = {2016}
}

@InProceedings{Yambay_ISBA_2017,

  author    = {David Yambay and Brian Walczak and Stephanie Schuckers and Adam Czajka},

  title     = {LivDet-Iris 2015 - Iris Liveness Detection Competition 2015},

  booktitle = {{IEEE} International Conference on Identity, Security and Behavior Analysis (ISBA)},

  year      = {2017},

  publisher = {IEEE},

  address   = {New Delhi, India},

  pages     = {1-6},

  month     = {Feb},

  abstract  = {Presentation attacks such as printed iris images or patterned contact lenses can be used to circumvent an iris recognition system. Different solutions have been proposed to counteract this vulnerability with Presentation Attack Detection (commonly called liveness detection) being used to detect the presence of an attack, yet independent evaluations and comparisons are rare. To fill this gap we have launched the first international iris liveness competition in 2013. This paper presents detailed results of its second edition, organized in 2015 (LivDet-Iris 2015). Four software-based approaches to Presentation Attack Detection were submitted. Results were tallied across three different iris datasets using a standardized testing protocol and large quantities of live and spoof iris images. The Federico Algorithm received the best results with a rate of rejected live samples of 1.68% and rate of accepted spoof samples of 5.48%. This shows that simple static attacks based on paper printouts and printed contact lenses are still challenging to be recognized purely by software-based approaches. Similar to the 2013 edition, printed iris images were easier to be differentiated from live images in comparison to patterned contact lenses.},

  doi       = {10.1109/ISBA.2017.7947701},

  keywords  = {Error analysis;Image color analysis;Iris;Iris recognition;Lenses;Training},

}

@article{srinivas2016human,

  title={Human Identification Using Automatic and Semi-Automatically Detected Facial Marks},

  author={Srinivas, Nisha and Flynn, Patrick J and Vorder Bruegge, Richard W},

  journal={Journal of forensic sciences},

  volume={61},

  pages={S117--S130},

  year={2016},

  publisher={Wiley Online Library}

}

@article{MERY2015260,

title = "Automatic facial attribute analysis via adaptive sparse representation of random patches",

journal = "Pattern Recognition Letters",

volume = "68",

pages = "260 - 269",

year = "2015",

note = "Special Issue on “Soft Biometrics”",

issn = "0167-8655",

doi = "https://doi.org/10.1016/j.patrec.2015.05.005",

url = "http://www.sciencedirect.com/science/article/pii/S0167865515001506",

author = "Domingo Mery and Kevin Bowyer",

keywords = "Soft biometrics, Expression recognition, Gender recognition, Race recognition, Sparse representations, Facial attribute analysis"

}

@article{bowyer2015critical,

  title={Critical examination of the IREX VI results},

  author={Bowyer, Kevin W and Ortiz, Estefan},

  journal={IET Biometrics},

  volume={4},

  number={4},

  pages={192--199},

  year={2015},

  publisher={IET}

}

@article{Rattani_2015_TIFS,
author = {Ajita Rattani and Walter J. Scheirer and Arun Ross},
title = {Open Set Fingerprint Spoof Detection Across Novel Fabrication Materials},
journal = {IEEE Transactions on Information Forensics and Security (T-IFS)},
volume = {10},
issue = {11},
month = {November},
year = {2015}
}

@article{CAMENT20153371,

title = "Face recognition under pose variation with local Gabor features enhanced by Active Shape and Statistical Models",

journal = "Pattern Recognition",

volume = "48",

number = "11",

pages = "3371 - 3384",

year = "2015",

issn = "0031-3203",

doi = "https://doi.org/10.1016/j.patcog.2015.05.017",

url = "http://www.sciencedirect.com/science/article/pii/S003132031500196X",

author = "Leonardo A. Cament and Francisco J. Galdames and Kevin W. Bowyer and Claudio A. Perez",

keywords = "Face recognition across pose, Statistical model for face recognition, Active shape model, Gabor features, Entropy weighting"

}

@ARTICLE{7264974, 

author={J. S. Doyle and K. W. Bowyer}, 

journal={IEEE Access}, 

title={Robust Detection of Textured Contact Lenses in Iris Recognition Using BSIF}, 

year={2015}, 

volume={3}, 

number={}, 

pages={1672-1683}, 

keywords={image classification;image segmentation;image texture;iris recognition;object detection;BSIF;classification rate;iris recognition;iris region segmentation;iris sensor;robust textured contact lenses detection;Classification algorithms;Contact lenses;Detection algorithms;Detectors;Eyes;Image processing;Image segmentation;Iris recognition;Lenses;Biometrics;image classification;image processing;image texture analysis;machine learning}, 

doi={10.1109/ACCESS.2015.2477470}, 

ISSN={}, 

month={},}

@inproceedings{Yadav:2015:PND:2808719.2808727,

 author = {Yadav, Nikhil and Poellabauer, Christian and Daudet, Louis and Collins, Tom\'{a}s and McQuillan, Shane and Flynn, Patrick},

 title = {Portable Neurological Disease Assessment Using Temporal Analysis of Speech},

 booktitle = {Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics},

 series = {BCB '15},

 year = {2015},

 isbn = {978-1-4503-3853-0},

 location = {Atlanta, Georgia},

 pages = {77--85},

 numpages = {9},

 url = {http://doi.acm.org/10.1145/2808719.2808727},

 doi = {10.1145/2808719.2808727},

 acmid = {2808727},

 publisher = {ACM},

 address = {New York, NY, USA},

 keywords = {concussions, portable diagnostics, speech analysis, voice pathology},

} 

@InProceedings{Trokielewicz_BTAS_2015,

  author    = {Mateusz Trokielewicz and Adam Czajka and Piotr Maciejewicz},

  title     = {Assessment of iris recognition reliability for eyes affected by ocular pathologies},

  booktitle = {{IEEE} International Conference on Biometrics: Theory Applications and Systems (BTAS)},

  year      = {2015},

  pages     = {1-6},

  address   = {Arlington, USA},

  month     = {September},

  abstract  = {This paper presents an analysis of how the iris recognition is impacted by eye diseases and an appropriate dataset comprising 2996 iris images of 230 distinct eyes (including 184 illness-affected eyes representing more than 20 different eye conditions). The images were collected in near infrared and visible light during a routine ophthalmological practice. The experimental study shows four valuable results. First, the enrollment process is highly sensitive to those eye conditions that make the iris obstructed or introduce geometrical distortions. Second, even those conditions that do not produce visible changes to the iris structure may increase the dissimilarity among samples of the same eyes. Third, eye conditions affecting iris geometry, its tissue structure or producing obstructions significantly decrease the iris recognition reliability. Fourth, for eyes afflicted by a disease, the most prominent effect of the disease on iris recognition is to cause segmentation errors. To our knowledge this is the first database of iris images for disease-affected eyes made publicly available to researchers, and the most comprehensive study of what we can expect when the iris recognition is deployed for non-healthy eyes.},

  day       = {8--11},

  doi       = {10.1109/BTAS.2015.7358747},

  keywords  = {diseases;eye;image segmentation;infrared imaging;iris recognition;medical image processing;vision defects;disease-affected eyes;eye conditions;eye diseases;geometrical distortions;illness-affected eyes;iris geometry;iris image database;iris recognition reliability assessment;iris structure;near infrared;ocular pathologies;ophthalmological practice;segmentation errors;tissue structure;visible changes;visible light;Cornea;Databases;Diseases;Iris;Iris recognition;Lenses;Pathology},

}

@InProceedings{,

  author    = {A. Czajka and K. W. Bowyer},

  title     = {Statistical evaluation of up-to-three-attempt iris recognition},

  booktitle = {{IEEE} International Conference on Biometrics Theory, Applications and Systems (BTAS)},

  year      = {2015},

  pages     = {1-6},

  month     = {Sept},

  abstract  = {Real-world biometric applications often operate in the context of an identity transaction that allows up to three attempts. That is, if a biometric sample is acquired and if it does not result in a match, the user is allowed to acquire a second sample, and if it again does not result in a match, the user is allowed to acquire a third sample. If the third sample does not result in a match, then the transaction is ended with no match. We report results of an experiment to determine whether or not successive attempts can be considered as independent samples from the same distribution, and whether and how the quality of a biometric sample changes in successive attempts. To our knowledge, this is the first published research to investigate the statistics of multi-attempt biometric transactions. We find that the common assumption that the attempt outcomes come from independent and identically distributed random variables in multi-attempt biometric transactions is incorrect.},

  doi       = {10.1109/BTAS.2015.7358797},

  keywords  = {image matching;iris recognition;statistical analysis;biometric application;biometric matching;biometric sample acquisition;biometric sample quality;distributed random variables;identity transaction;multiattempt biometric transaction;statistical evaluation;up-to-three-attempt iris recognition;Authentication;Cameras;High definition video;Iris recognition;Sociology;Statistics},

}

@INPROCEEDINGS{7358780, 

author={J. Bernhard and J. Barr and K. W. Bowyer and P. Flynn}, 

booktitle={2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS)}, 

title={Near-IR to visible light face matching: Effectiveness of pre-processing options for commercial matchers}, 

year={2015}, 

volume={}, 

number={}, 

pages={1-8}, 

keywords={face recognition;feature extraction;image matching;infrared imaging;ND-NIVL;commercial matchers;face recognition;illumination issues;image preprocessing techniques;near infrared visible light database;near-IR face images;red plane extraction;standard visible light face matching;visible light images;Adaptive equalizers;Databases;Face;Histograms;Image resolution;Lighting;Springs}, 

doi={10.1109/BTAS.2015.7358780}, 

ISSN={}, 

month={Sept},}

@article{Rocha_2015_JIVP,
author = {Anderson Rocha and Walter J. Scheirer},
title = {Large-scale learning for media understanding},
journal = {EURASIP Journal on Image and Video Processing (JIVP)},
volume = {2015},
number = {24},
month = {July},
year = {2015}
}

@InProceedings{Trokielewicz_CYBCONF_2015,

  author    = {M. Trokielewicz and A. Czajka and P. Maciejewicz},

  title     = {Database of iris images acquired in the presence of ocular pathologies and assessment of iris recognition reliability for disease-affected eyes},

  booktitle = {{IEEE} International Conference on Cybernetics (CYBCONF)},

  year      = {2015},

  pages     = {495-500},

  address   = {Gdynia, Poland},

  month     = {June},

  publisher = {IEEE},

  abstract  = {This paper presents a database of iris images collected from disease affected eyes and an analysis related to the influence of ocular diseases on iris recognition reliability. For that purpose we have collected a database of iris images acquired for 91 different eyes during routine ophthalmology visits. This collection gathers samples for healthy eyes as well as those with various eye pathologies, including cataract, acute glaucoma, posterior and anterior synechiae, retinal detachment, rubeosis iridis, corneal vascularization, corneal grafting, iris damage and atrophy and corneal ulcers, haze or opacities. To our best knowledge this is the first database of such kind that will be made publicly available. In the analysis the data were divided into five groups of samples presenting similar anticipated impact on iris recognition: 1) healthy (no impact), 2) unaffected, clear iris (although the illness was detected), 3) geometrically distorted irides, 4) distorted iris tissue and 5) obstructed iris tissue. Three different iris recognition methods (MIRLIN, VeriEye and OSIRIS) were then used to find differences in average genuine and impostor comparison scores calculated for healthy eyes and those impacted by a disease. Specifically, we obtained significantly worse genuine comparison scores for all iris matchers and all disease-affected eyes when compared to a group of healthy eyes, what have a high potential of impacting false non-match rate.},

  day       = {24--26},

  doi       = {10.1109/CYBConf.2015.7175984},

  keywords  = {diseases;eye;image matching;iris recognition;visual databases;MIRLIN;OSIRIS;VeriEye;acute glaucoma;anterior synechiae;atrophy;cataract;corneal grafting;corneal ulcer;corneal vascularization;disease-affected eyes;distorted iris tissue;eye pathology;false nonmatch rate;geometrically distorted irides;haze;healthy eyes;illness;iris damage;iris image database;iris recognition reliability assessment;obstructed iris tissue;ocular disease;ocular pathology;opacity;posterior synechiae;retinal detachment;routine ophthalmology visit;rubeosis iridis;Biomedical imaging;Databases;Diseases;Geometry;Iris recognition;Lenses;Pathology;eye conditions;iris image databases;iris recognition;performance evaluation},

}

@InProceedings{Czajka_CYBCONF_2015,

  author    = {Adam Czajka and Kevin W. Bowyer},

  title     = {Statistical analysis of multiple presentation attempts in iris recognition},

  booktitle = {{IEEE} International Conference on Cybernetics (CYBCONF)},

  year      = {2015},

  pages     = {483-488},

  address   = {Gdynia, Poland},

  month     = {June},

  publisher = {IEEE},

  abstract  = {This paper presents experimental results showing uneven distributions of selected iris image quality metrics in the consecutive attempts in a biometric system that allows for multiple attempts to complete a transaction. We consider three iris image quality metrics that can be influenced by user behavior: usable iris area, motion blur and margin adequacy. The quality metrics are used to judge the overall quality of the iris image and accept or reject it on each attempt. The experiment simulates a typical physical access scenario with a maximum of three attempts in one transaction. One conclusion is that subjects rejected on the first attempt do, on average, improve the quality of their iris image on their second attempt. If their second image is rejected, the average quality improvement on the third attempt is lower. A second conclusion is that the probability of a subject being rejected on the second try is higher in average than the probability calculated for all subjects delivering their first samples. The latter finding contrasts with a common belief that each try in a single transaction can be assumed to be a draw from the same authentic distribution (and hence the rejection probabilities are equal in each try). A third interesting and surprising observation is that improvement of sample quality is higher for women than for men. To our knowledge, this paper presents the first research explaining the nature of multi-attempt iris recognition system and delivers conclusions that suggest that the default understanding of this process is too simplistic.},

  day       = {24--26},

  doi       = {10.1109/CYBConf.2015.7175982},

  keywords  = {image motion analysis;image restoration;iris recognition;probability;statistical analysis;biometric system;iris image quality metrics;iris recognition;margin adequacy;motion blur;multiple presentation attempts;rejection probabilities;statistical analysis;usable iris area;user behavior;Cameras;Image quality;Iris;Iris recognition;Measurement;Sociology;Statistics;iris image quality;iris recognition;multiple-attempt system;statistical analysis},

}

@InProceedings{10.1007/978-3-319-30285-0_5,

author="Banerjee, Sandipan

and Mery, Domingo",

editor="Huang, Fay

and Sugimoto, Akihiro",

title="Iris Segmentation Using Geodesic Active Contours and GrabCut",

booktitle="Image and Video Technology -- PSIVT 2015 Workshops",

year="2016",

publisher="Springer International Publishing",

address="Cham",

pages="48--60",

abstract="Iris segmentation is an important step in iris recognition as inaccurate segmentation often leads to faulty recognition. We propose an unsupervised, intensity based iris segmentation algorithm in this paper. The algorithm is fully automatic and can work for varied levels of occlusion, illumination and different shapes of the iris. A near central point inside the pupil is first detected using intensity based profiling of the eye image. Using that point as the center, we estimate the outer contour of the iris and the contour of the pupil using geodesic active contours, an iterative energy minimization algorithm based on the gradient of intensities. The iris region is then segmented out using both these estimations by applying an automatic version of GrabCut, an energy minimization algorithm from the graph cut family, representing the image as a Markov random field. The final result is refined using an ellipse-fitting algorithm based on the geometry of the GrabCut segmentation. To test our method, experiments were performed on 600 near infra-red eye images from the GFI database. The following features of the iris image are estimated: center and radius of the pupil and the iris. In order to evaluate the performance, we compare the features obtained by our method and the segmentation modules of three popular iris recognition systems with manual segmentation (ground truth). The results show that the proposed method performs as good as, in many cases better, when compared with these systems.",

isbn="978-3-319-30285-0"

}

@ARTICLE{7039210, 

author={A. Sgroi and P. J. Flynn and K. Bowyer and P. J. Phillips}, 

journal={IEEE Transactions on Information Forensics and Security}, 

title={Strong, Neutral, or Weak: Exploring the Impostor Score Distribution}, 

year={2015}, 

volume={10}, 

number={6}, 

pages={1207-1220}, 

keywords={face recognition;fingerprint identification;image matching;iris recognition;SNoW concept;face recognition system;fingerprint recognition;impostor score distribution;iris recognition;partition stability;strong-neutral-weak face impostor pair problem;Algorithm design and analysis;Face;Face recognition;Partitioning algorithms;Probes;Snow;Standards;Biometrics;biometrics;face recognition;fingerprint recognition;iris recognition;performance evaluation}, 

doi={10.1109/TIFS.2015.2403136}, 

ISSN={1556-6013}, 

month={June},}

@InProceedings{Ortiz_2015_CVPR_Workshops,

author = {Ortiz, Estefan and Bowyer, Kevin W.},

title = {Exploratory Analysis of an Operational Iris Recognition Dataset From a CBSA Border-Crossing Application},

booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},

month = {June},

year = {2015}

}

@proceeding{doi: 10.1117/12.2181981,

author = { Christopher  Boehnen,David  Bolme,Patrick  Flynn},

title = {Biometrics IRB best practices and data protection},

journal = {Proc.SPIE},

volume = {9457},

number = {},

pages = {9457 - 9457 - 7},

year = {2015},

doi = {10.1117/12.2181981},

URL = {https://doi.org/10.1117/12.2181981},

eprint = {}

}

@INPROCEEDINGS{7284808, 

author={}, 

booktitle={2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)}, 

title={B-WILD 2015: Biometrics in the Wild}, 

year={2015}, 

volume={02}, 

number={}, 

pages={1-2}, 

keywords={}, 

doi={10.1109/FG.2015.7284808}, 

ISSN={}, 

month={May},}

@article{PHILLIPS201796,

title = "Lessons from collecting a million biometric samples",

journal = "Image and Vision Computing",

volume = "58",

pages = "96 - 107",

year = "2017",

issn = "0262-8856",

doi = "https://doi.org/10.1016/j.imavis.2016.08.004",

url = "http://www.sciencedirect.com/science/article/pii/S0262885616301287",

author = "P. Jonathon Phillips and Patrick J. Flynn and Kevin W. Bowyer",

keywords = "Face recognition, Algorithm performance, Human performance, Challenge problem"

}

@INPROCEEDINGS{7284833, 

author={K. W. Bowyer and E. Ortiz and A. Sgroi}, 

booktitle={2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)}, 

title={Trial Somaliland voting register de-duplication using iris recognition}, 

year={2015}, 

volume={02}, 

number={}, 

pages={1-8}, 

keywords={government data processing;image classification;image matching;iris recognition;2010 Somaliland presidential election;forensic iris matching;image matching;iris recognition;trial Somaliland voting register deduplication;voter registration;Error analysis;Fingerprint recognition;Forensics;Iris;Iris recognition;Nominations and elections;Registers}, 

doi={10.1109/FG.2015.7284833}, 

ISSN={}, 

month={May},}

@INPROCEEDINGS{7284812, 

author={A. Sgroi and H. Garvey and K. Bowyer and P. Flynn}, 

booktitle={2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)}, 

title={Location matters: A study of the effects of environment on facial recognition for biometric security}, 

year={2015}, 

volume={02}, 

number={}, 

pages={1-7}, 

keywords={face recognition;image matching;security of data;visual databases;FRVT 2006 dataset;acquisition locations;biometric security;cross-environment image matching;environment recognition;face recognition accuracy;gallery images;location matters;probe images;within-environment image matching;Accuracy;Face;Face recognition;Indoor environments;Lighting;Probes;Security}, 

doi={10.1109/FG.2015.7284812}, 

ISSN={}, 

month={May},}

@Article{Czajka_TIFS_2015,

  author    = {Adam Czajka},

  title     = {Pupil Dynamics for Iris Liveness Detection},

  journal   = {{IEEE} Transactions on Information Forensics and Security},

  year      = {2015},

  volume    = {10},

  number    = {4},

  pages     = {726-735},

  month     = {April},

  issn      = {1556-6013},

  abstract  = {The primary objective of this paper is to propose a complete methodology for eye liveness detection based on pupil dynamics. This method may serve as a component of presentation attack detection in iris recognition systems, making them more secure. Due to a lack of public databases that would support this paper, we have built our own iris capture device to register pupil size changes under visible light stimuli, and registered 204 observations for 26 subjects (52 different irides), each containing 750 iris images taken every 40 ms. Each measurement registers the spontaneous pupil oscillations and its reaction after a sudden increase of the intensity of visible light. The Kohn and Clynes pupil dynamics model is used to describe these changes; hence we convert each observation into a feature space defined by model parameters. To answer the question whether the eye is alive (that is, if it reacts to light changes as a human eye) or the presentation is suspicious (that is, if it reacts oddly or no reaction is observed), we use linear and nonlinear support vector machines to classify natural reaction and spontaneous oscillations, simultaneously investigating the goodness of fit to reject bad modeling. Our experiments show that this approach can achieve a perfect performance for the data we have collected. All normal reactions are correctly differentiated from spontaneous oscillations. We investigated the shortest observation time required to model the pupil reaction, and found that time periods not exceeding 3 s are adequate to offer a perfect performance.},

  comment   = {iris:PAD:dynamic:active},

  doi       = {10.1109/TIFS.2015.2398815},

  keywords  = {computer crime;feature extraction;image classification;iris recognition;support vector machines;eye liveness detection;feature space;iris capture device;iris images;iris liveness detection;iris recognition systems;model parameters;natural reaction classification;nonlinear support vector machines;presentation attack detection;pupil dynamics;pupil oscillations;pupil size changes;spontaneous oscillations;visible light intensity;visible light stimuli;Cameras;Databases;Iris recognition;Lenses;Motion pictures;Oscillators;Liveness detection;biometrics;iris recognition;presentation attack detection;pupil dynamics},

  publisher = {IEEE},

}

@article{poellabauer2015challenges,

  title={Challenges in concussion detection using vocal acoustic biomarkers},

  author={Poellabauer, Christian and Yadav, Nikhil and Daudet, Louis and Schneider, Sandra L and Busso, Carlos and Flynn, Patrick J},

  journal={IEEE Access},

  volume={3},

  pages={1143--1160},

  year={2015},

  publisher={IEEE}

}

@inproceedings{beveridge2015report,

  title={Report on the FG 2015 video person recognition evaluation},

  author={Beveridge, J Ross and Zhang, Hao and Draper, Bruce A and Flynn, Patrick J and Feng, Zhenhua and Huber, Patrik and Kittler, Josef and Huang, Zhiwu and Li, Shaoxin and Li, Yan and others},

  booktitle={IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)},

  year={2015},

  organization={IEEE}

}

@INPROCEEDINGS{7084295, 

author={A. Sgroi and K. Bowyer and P. Flynn}, 

booktitle={2014 IEEE International Workshop on Information Forensics and Security (WIFS)}, 

title={Metadata-based understanding of impostor pair score variations}, 

year={2014}, 

volume={}, 

number={}, 

pages={7-12}, 

keywords={face recognition;image matching;meta data;SNoW technique;face image;impostor image pair;impostor pair score variation;matching metadata value;metadata matches;metadata-based understanding;probe images;Algorithm design and analysis;Face;Face recognition;Image recognition;Market research;Partitioning algorithms;Snow;biometrics;face recognition;metadata;score analysis}, 

doi={10.1109/WIFS.2014.7084295}, 

ISSN={2157-4766}, 

month={Dec},}

@InProceedings{Trokielewicz_SPIE_2014,

  author    = {Mateusz Trokielewicz and Adam Czajka and Piotr Maciejewicz},

  title     = {Cataract influence on iris recognition performance},

  booktitle = {Proceedings of SPIE},

  year      = {2014},

  volume    = {9290},

  pages     = {9290-9290-14},

  month     = {November},

  abstract  = {This paper presents the experimental study revealing weaker performance of the automatic iris recognition methods for cataract-affected eyes when compared to healthy eyes. There is little research on the topic, mostly incorporating scarce databases that are often deficient in images representing more than one illness. We built our own database, acquiring 1288 eye images of 37 patients of the Medical University of Warsaw. Those images represent several common ocular diseases, such as cataract, along with less ordinary conditions, such as iris pattern alterations derived from illness or eye trauma. Images were captured in near-infrared light (used in biometrics) and for selected cases also in visible light (used in ophthalmological diagnosis). Since cataract is a disorder that is most populated by samples in the database, in this paper we focus solely on this illness. To assess the extent of the performance deterioration we use three iris recognition methodologies (commercial and academic solutions) to calculate genuine match scores for healthy eyes and those influenced by cataract. Results show a significant degradation in iris recognition reliability manifesting by worsening the genuine scores in all three matchers used in this study (12% of genuine score increase for an academic matcher, up to 175% of genuine score increase obtained for an example commercial matcher). This increase in genuine scores affected the final false non-match rate in two matchers. To our best knowledge this is the only study of such kind that employs more than one iris matcher, and analyzes the iris image segmentation as a potential source of decreased reliability},

  day       = {25},

  doi       = {10.1117/12.2076040},

}

@InCollection{Czajka_CCIS_2014,

  author    = {Adam Czajka},

  title     = {Influence of Iris Template Aging on Recognition Reliability},

  booktitle = {Communications in Computer and Information Science},

  publisher = {Springer},

  year      = {2014},

  volume    = {452},

  pages     = {284-299},

  abstract  = {The paper presents an iris aging analysis based on comparison results obtained for four different iris matchers. We collected an iris aging database of samples captured even eight years apart. To our best knowledge, this is the only database worldwide of iris images collected with such a large time distance between capture sessions. We evaluated the influence of the intra- vs. inter-session accuracy of the iris recognition, as well as the accuracy between the short term (up to two years) vs. long term comparisons (from 5 to 9 years). The average genuine scores revealed statistically significant differences with respect to the time distance between examined samples (up to 14 % of degradation in the average genuine scores is observed). These results may suggest that the iris pattern ages to some extent, and thus appropriate countermeasures should be deployed in application assuming large time distances between iris template replacements (or adaptations).},

  doi       = {https://doi.org/10.1007/978-3-662-44485-6\_20},

  keywords  = {biometric template aging;Iris recognition;biometrics},

}

@ARTICLE{6905835, 

author={J. R. Barr and K. W. Bowyer and P. J. Flynn}, 

journal={IEEE Transactions on Information Forensics and Security}, 

title={Framework for Active Clustering With Ensembles}, 

year={2014}, 

volume={9}, 

number={11}, 

pages={1986-2001}, 

keywords={Clustering algorithms;Face;Face recognition;Labeling;Measurement;Noise;Partitioning algorithms}, 

doi={10.1109/TIFS.2014.2359369}, 

ISSN={1556-6013}, 

month={Nov},

}

@INPROCEEDINGS{7038943, 

author={N. Yadav and L. Daudet and C. Poellabauer and P. Flynn}, 

booktitle={2014 IEEE Healthcare Innovation Conference (HIC)}, 

title={Noise management in mobile speech based health tools}, 

year={2014}, 

volume={}, 

number={}, 

pages={335-338}, 

keywords={health care;medical disorders;microphones;smart phones;speech;speech recognition;telemedicine;acoustic environment;microphone;mobile devices;mobile health tools;mobile speech;noise management;signal-to-noise ratio;speech disorder detector;speech processing capabilities;speech recognition accuracy;word accuracy;Accuracy;Acoustics;Mobile communication;Signal to noise ratio;Speech;Speech recognition}, 

doi={10.1109/HIC.2014.7038943}, 

ISSN={}, 

month={Oct},}

@InProceedings{Yambay_IJCB_2014,

  author    = {David Yambay and James S. Doyle and Kevin W. Bowyer and Adam Czajka and Stephanie Schuckers},

  title     = {LivDet-iris 2013 - Iris Liveness Detection Competition 2013},

  booktitle = {{IEEE} International Joint Conference on Biometrics (IJCB)},

  address   = {Clearwater, FL, USA},

  publisher = {IEEE},

  year      = {2014},

  pages     = {1-8},

  month     = {Sept},

  abstract  = {The use of an artificial replica of a biometric characteristic in an attempt to circumvent a system is an example of a biometric presentation attack. Liveness detection is one of the proposed countermeasures, and has been widely implemented in fingerprint and iris recognition systems in recent years to reduce the consequences of spoof attacks. The goal for the Liveness Detection (LivDet) competitions is to compare software-based iris liveness detection methodologies using a standardized testing protocol and large quantities of spoof and live images. Three submissions were received for the competition Part 1; Biometric Recognition Group de Universidad Autonoma de Madrid, University of Naples Federico II, and Faculdade de Engenharia de Universidade do Porto. The best results from across all three datasets was from Federico with a rate of falsely rejected live samples of 28.6% and the rate of falsely accepted fake samples of 5.7%.},

  comment   = {iris:PAD},

  doi       = {10.1109/BTAS.2014.6996283},

  keywords  = {iris recognition;Biometric Recognition Group de Universidad Autonoma de Madrid;Faculdade de Engenharia de Universidade do Porto;Iris Liveness Detection Competition 2013;LivDet-iris 2013;University of Naples Federico II;biometric characteristic;biometric presentation attack;fingerprint recognition system;iris recognition system;software-based iris liveness detection methodologies;spoof attacks;standardized testing protocol;Cameras;Educational institutions;Iris;Iris recognition;Lenses;Testing;Training},

}

@INPROCEEDINGS{6996297, 

author={E. Ortiz and K. W. Bowyer and P. J. Flynn}, 

booktitle={IEEE International Joint Conference on Biometrics}, 

title={An optimal strategy for dilation based iris image enrollment}, 

year={2014}, 

volume={}, 

number={}, 

pages={1-6}, 

keywords={approximation theory;image matching;iris recognition;approximate linear relationship;iris biometrics;iris image enrollment;matching errors;optimal strategy;pupil dilation;Analytical models;Equations;Iris;Iris recognition;Mathematical model;NIST;Probes}, 

doi={10.1109/BTAS.2014.6996297}, 

ISSN={}, 

month={Sept},}

@InProceedings{10.1007/978-3-319-16181-5_57,

author="Tapia, Juan E.

and Perez, Claudio A.

and Bowyer, Kevin W.",

editor="Agapito, Lourdes

and Bronstein, Michael M.