Kevin W. Bowyer - Iris Recognition

  • Analysis of diurnal changes in pupil dilation and eyelid aperture,
    Adam Czajka, Kevin W. Bowyer and Estefan Ortiz,
    IET Biometrics 7 (2), March 2018, 136-144.
    DOI link to this paper in IEEE Xplore.
    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.

  • Recognition of image-orientation-based iris spoofing,
    Adam Czajka, Kevin W. Bowyer, Michael Krumdick, and Rosaura G. VidalMata,
    IEEE Transactions on Information Forensics and Security 12 (9), September 2017, 2184 - 2196.
    DOI link to this paper in IEEE Xplore.
    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.

  • Lessons from Collecting a Million Biometric Samples,
    P. Jonathon Phillips, Patrick J. Flynn and Kevin W. Bowyer,
    Image and Vision Computing Journal 58, 96–107, February 2017.
    DOI link to this paper in ScienceDirect.
    Over the past decade, independent evaluations have become commonplace in many areas of experimental computer science, including face and gesture recognition. A key attribute of many successful independent evaluations is a curated data set. Desired aspects associated with these data sets include appropriateness to the experimental design, a corpus size large enough to allow statistically rigorous characterization of results, and the availability of comprehensive metadata that allow inferences to be made on various data set attributes. In this paper, we review a ten-year biometric sampling effort that enabled the creation of several key biometrics challenge problems. We summarize the design and execution of data collections, identify key challenges, and convey some lessons learned.

  • A Method for 3D Iris Reconstruction from Multiple 2D Near-Infrared Images,
    Diego Bastias; Claudio A. Perez; Daniel P. Benalcazar; Kevin W. Bowyer Claudio Perez, Diego Bastias and Kevin Bowyer,
    IEEE International Joint Conference on Biometrics, October 2017, Denver.
    DOI link to this paper in IEEE Xplore.
    The need to verify identity has become an everyday experience for most people. Biometrics is the principal means for reliable identification of people. Although iris recognition is the most reliable current technique for biometric identification, it has limitations because only segments of the iris are available due to occlusions from the eyelids, eyelashes, specular highlights, etc. The goal of this research is to study iris reconstruction from several 2D near infrared iris images, adding depth information to iris recognition. We expect that adding depth information from the iris surface will make it possible to identify people from a smaller segment of the iris. We designed a sensor for 2D near-infrared iris image acquisition. The method follows a pre-processing stage with the goal of performing iris enhancement, eliminating occlusions, reflections and extreme gray-level values, ending in iris texture equalization. The last step is the 3D iris model reconstruction based on several 2D iris images acquired at different angles. Results from each stage are presented.

  • LivDet Iris 2017 - Iris Liveness Detection Competition 2017,
    David Yambay, Benedict Becker, Naman Kohli, Daksha Yadav, Adam Czajka, Kevin W. Bowyer, Stephanie Schuckers, Richa Singh, Mayank Vatsa, Afzel Noore, D. Gragnaniello, C. Sansone, L. Verdoliva, Lingxiao He, Yiwei Ru, Haiqing Li, Nianfeng Liu, Zhenan Sun, Tieniu Tan,
    IEEE International Joint Conference on Biometrics, October 2017, Denver.
    DOI link to this paper in IEEE Xplore.
    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. The first international iris liveness competition was launched in 2013 in order to assess the performance of presentation attack detection (PAD) algorithms, with a second competition in 2015. This paper presents results of the third competition, LivDet-Iris 2017. Three software-based approaches to Presentation Attack Detection were submitted. Four datasets of live and spoof images were tested with an additional cross-sensor test. New datasets and novel situations 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, printed 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 comparison to patterned contact lenses as was also seen in previous competitions.

  • Gender-From-Iris or Gender-From-Mascara?,
    Andrey Kuehlkamp, Benedict Becker and Kevin Bowyer,
    IEEE Winter Conference on Applications of Computer Vision (WACV), March 2017.
    DOI link to this paper in IEEE Xplore.
    Predicting a person's gender based on the iris texture has been explored by several researchers. This paper considers several dimensions of experimental work on this problem, including person-disjoint train and test, and the effect of cosmetics on eyelash occlusion and imperfect segmentation. We also consider the use of multi-layer perceptron and convolutional neural networks as classifiers, comparing the use of data-driven and hand-crafted features. Our results suggest that the gender-from-iris problem is more difficult than has so far been appreciated. Estimating accuracy using a mean of N person-disjoint train and test partitions, and considering the effect of makeup - a combination of experimental conditions not present in any previous work - we find a much weaker ability to predict gender-from-iris texture than has been suggested in previous work.

  • Handbook of Iris Recognition, second edition,
    Kevin W. Bowyer and Mark J. Burge, editors,
    Springer, 2016.
    Springer page.
    Jim Wayman's Afterword to the Second Edition.

  • Pitfalls In Studying "Big Data" From Operational Scenarios,
    Estefan Ortiz and Kevin W. Bowyer,
    IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS), September 2016.
    pdf of this paper.
    Analyzing a larger dataset is sometimes assumed, in itself, to give a greater degree of validity to the results of a study. In biometrics, analyzing an “operational” dataset is also sometimes assumed, in itself, to give a greater degree of validity. And so studying a large, operational biometric dataset may seem to guarantee valid results. However, a number of basic questions should be asked of any “found” big data, in order to avoid pitfalls of the data not being suitable for the desired analysis. We explore such issues using a large operational iris recognition dataset from the Canada Border Services Agency’s NEXUS program, similar to the dataset analyzed in the NIST IREX VI report.

  • Biometric Identification of Identical Twins: A Survey
    Kevin W. Bowyer and Patrick J. Flynn,
    IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS), September 2016.
    pdf of this paper.
    The ability of biometric techniques to distinguish between identical twins is of interest for multiple reasons. The research literature touching on this topic is spread across a variety of areas. This survey pulls together the literature to date in this area, identifies available datasets for research, points out topics of uncertainty and suggests possible future research.

  • On accuracy estimation and comparison of results in biometric research,
    Domingo Mery, Yuning Zhao and Kevin Bowyer,
    IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS), September 2016.
    pdf of this paper.
    The estimated accuracy of an algorithm is the most important element of the typical biometrics research publication. Comparisons between algorithms are commonly made based on estimated accuracies reported in different publications. However, even when the same dataset is used in two publications, there is a very low frequency of the publications using the same protocol for estimating algorithm accuracy. Using the example problems of face recognition, expression recognition and gender classification, we show that the variation in estimated performance on the same dataset across different protocols can be enormous. Based on these results, we make recommendations for how to obtain performance estimates that allow reliable comparison between algorithms.

    An Analysis of 1-to-First Matching in Iris Recognition
    Andrey Kuehlkamp and Kevin W. Bowyer,
    IEEE Workshop on Applications of Computer Vision, March 2016.
    pdf of this paper.
    ... A 1-to-First search terminates with the first below-threshold match that is found, whereas a 1-to-N search always finds the best match across all enrollments. We know of no previous studies that evaluate how the accuracy of 1-to-First search differs from that of 1-to-N search. Using a dataset of over 50,000 iris images from 2,800 different irises, we perform experiments to evaluate the relative accuracy of 1-to-First and 1-to-N search. We evaluate how the accuracy difference changes with larger numbers of enrolled irises, and with larger ranges of rotational difference allowed between iris images. We find that False Match error rate for 1-to- First is higher than for 1-to-N, and the the difference grows with larger number of enrolled irises and with larger range of rotation.

  • Critical Examination of the IREX VI Results,
    Kevin W. Bowyer and Estefan Ortiz,
    IET Biometrics 4 (4), 2015, 192-199.
    pdf of this paper.
    The authors analyse why Iris Exchange Report (IREX) VI conclusions about 'iris ageing' differ significantly from results of previous research on 'iris template ageing'. They observe that IREX VI uses a definition of 'iris ageing' that is restricted to a subset of International Organization for Standardization (ISO)-definition template ageing. They also explain how IREX VI commits various methodological errors in obtaining what it calls its 'best estimate of iris recognition ageing'. The OPS-XING dataset that IREX VI analyses for its 'best estimate of iris recognition ageing' contains no matches with Hamming distance >0.27. A 'truncated regression' technique should be used to analyse such a dataset, which IREX VI fails to do so, biasing its 'best estimate' to be lower-than-correct. IREX VI mixes Hamming distances from first, second and third attempts together in its regression, creating another source of bias towards a lower-than-correct value. In addition, the match scores in the OPS-XING dataset are generated from a '1-to-first' matching strategy, meaning that they contain a small but unknown number of impostor matches, constituting another source of bias towards an artificially low value for ageing. Finally, IREX VI makes its 'best estimate of iris recognition ageing' by interpreting its regression model without taking into account the correlation among independent variables. This is another source of bias towards an artificially low value for ageing. Importantly, the IREX VI report does not acknowledge the existence of any of these sources of bias. They conclude with suggestions for a revised, improved IREX VI.

  • Robust Detection of Textured Contact Lenses in Iris Recognition Using BSIF,
    James S. Doyle and Kevin W. Bowyer,
    IEEE Access, volume 3, 1672-1683, 14 September 2015, DOI: 10.1109/ACCESS.2015.2477470.
    link to this paper.
    This paper considers three issues that arise in creating an algorithm for the robust detection of textured contact lenses in iris recognition images. The first issue is whether the accurate segmentation of the iris region is required in order to achieve the accurate detection of textured contact lenses. Our experimental results suggest that accurate iris segmentation is not required. The second issue is whether an algorithm trained on the images acquired from one sensor will well generalize to the images acquired from a different sensor. Our results suggest that using a novel iris sensor can significantly degrade the correct classification rate of a detection algorithm trained with the images from a different sensor. The third issue is how well a detector generalizes to a brand of textured contact lenses, not seen in the training data. This paper shows that a novel textured lens type may have a significant impact on the performance of textured lens detection.

  • Dilation-Aware Enrollment for Iris Recognition,
    Estefan Ortiz, Kevin W. Bowyer and Patrick J. Flynn,
    IET Biometrics, DOI: 10.1049/iet-bmt.2015.0005. Available online: 13 October 2015.
    pdf of this paper.
    Iris recognition systems typically enroll a person based on a single "best" eye image. Research has shown that the probability of a false non-match result increases with increased difference in pupil dilation between the enrollment image and the probe image. Therefore, dilation-aware methods of enrollment should improve the accuracy of iris recognition. We examine a strategy to improve accuracy through a dilation-aware enrollment step that selects one or more enrollment images based on the observed distribution of dilation ratios for that eye. Additionally, we demonstrate that an image with median dilation is the optimal single eye image dilation-aware enrollment choice. Our results confirm that this dilation-aware enrollment strategy does improve matching accuracy compared to traditional single-image enrollment, and also compared to multi-image enrollment that does not take dilation into account.

  • Statistical Evaluation of Up-to-Three-Attempt Iris Recognition,
    Adam Czajka and Kevin W. Bowyer,
    IEEE International Conference on Biometrics Theory, Applications and Systems (BTAS 2015), to appear.
    pdf of this paper.
    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.

  • Exploratory Analysis of an Operational Iris Recognition Dataset from a CBSA Border-Crossing Application,
    Estefan Ortiz and Kevin W. Bowyer,
    CVPR Biometrics Workshop, June 2015.
    pdf of this paper.
    This paper presents an exploratory analysis of an iris recognition dataset from the NEXUS border-crossing program run by the Canadian Border Services Agency. The distribution of the normalized Hamming distance for successful border-crossing transactions is examined in the context of various properties of the operational scenario. The effects of properties such as match score censoring and truncation, same-sensor and cross-sensor matching, sequence-dependent matching, and multiple-kiosk matching are illustrated. Implications of these properties of the operational dataset for the study of iris template aging are discussed.

  • Trial Somaliland Voting Register De-duplication Using Iris Recognition,
    Kevin W. Bowyer, Estefan Ortiz and Amanda Sgroi,
    Biometrics in the Wild Workshop 2015 (BWild 2015), Ljubljana, Slovenia, May 2015.
    pdf of this paper.
    Face and fingerprint were used in de-duplication of the voter registration list for the 2010 Somaliland presidential election. Iris recognition was evaluated as a possible more powerful means of de-duplication of the voting register for the planned 2015 elections. On a trial dataset of 1,062 registration records, all instances of duplicate registration were detected and zero non-duplicates were falsely classified as duplicates, indicating the power of iris recognition for voting register deduplication. All but a tiny fraction of the cases were classified by automatic matching, and the remaining cases were classified by forensic iris matching. Images in this dataset reveal the existence of unusual eye conditions that consistently cause falsenon- match results. Examples are shown and discussed.

  • Lessons from collecting a million biometric samples,
    P. Jonathon Phillips, Patrick J. Flynn and Kevin W. Bowyer,
    IEEE International Conference on Automatic Face and Gesture Recognition (FG 2015), Ljubljana, Slovenia, May 2015.
    pdf of this paper.
    Over the past decade, independent evaluations have become commonplace in many areas of experimental computer science, including face and gesture recognition. A key attribute of many successful independent evaluations is a curated data set. Desired things associated with these data sets include appropriateness to the experimental design, a corpus size large enough to allow statistically rigorous characterization of results, and the availability of comprehensive metadata that allow inferences to be made on various data set attributes. In this paper, we review a ten-year biometric sampling effort that enabled the creation of several key biometrics challenge problems. We summarize the design and execution of data collections, identify key challenges, and convey some lessons learned.

  • Gender Classification from Iris Images Using Fusion of Uniform Local Binary Patterns,
    Juan E. Tapia, Claudio A. Perez and Kevin W. Bowyer,
    ECCV Workshop on Soft Biometrics, September 2014.
    pdf of this paper.
    ... Using a subject-disjoint test set, we are able to achieve over 91% correct gender prediction accuray using the texture of the iris. To our knowledge, this is the highest accuracy yet achieved for predicting gender from iris texture.

  • Cosmetic Contact Lenses and Iris Recognition Spoofing,
    Kevin W. Bowyer and James S. Doyle,
    IEEE Computer 47 (5), 96-98, May 2014.
    link to this paper in IEEE Xplore.
    Automatically detecting novel types of cosmetic contact lenses in iris images is a very difficult pattern-recognition problem, but experimental datasets that enable researchers to study this problem have recently become available.

  • Unraveling the Effect of Textured Contact Lenses on Iris Recognition,
    Daksha Yadav, Naman Kohli, James S. Doyle, Rich Singh, Mayank Vatsa and Kevin W. Bowyer,
    IEEE Transactions on Information Forensics and Security 9 (5), 851-862, May 2014.
    pdf of this paper.
    The presence of a contact lens, particularly a textured cosmetic lens, poses a challenge to iris recognition as it obfuscates the natural iris patterns. The main contribution of this paper is to present an in-depth analysis of the effect of contact lenses on iris recognition. Two databases, namely, IIITD Iris Contact Lens database and ND-Contact Lens database are prepared to analyze the variations caused due to contact lenses. We also present a novel lens detection algorithm that can be used to reduce the effect of contact lenses. The proposed approach outperforms other lens detection algorithms on the two databases and shows improved iris recognition performance.

  • Similarity of Iris Texture Between Siblings
    Will Vranderic and Kevin W. Bowyer,
    Biometrics Theory, Applications and Systems (BTAS), Sept 30 - Oct 2, 2013.
    pdf of this paper.
    Prior research has shown that twins' irises are similar enough in appearance for the untrained human observer to correctly determine whether an iris image pair comes from twins or from unrelated persons. We conducted a similar image pair classification study that asked participants to classify an image pair as ''siblings'' or ''unrelated''. We found that untrained human observers can classify pairs of siblings with over 57% accuracy using the appearance of the iris alone, without any proximal image content. This result is statistically greater than the accuracy of random guessing, which indicates that there is some degree of inherited texture similarity between siblings. This raises the question of how accurately one could classify siblings based on automated texture analysis.

  • Identity Verification Using Iris Images: Performance of Human Examiners,
    Kevin McGinn, Samuel Tarin and Kevin W. Bowyer,
    Biometrics Theory, Applications and Systems (BTAS), Sept 30 - Oct 2, 2013.
    pdf of this paper.
    We are not aware of any previous systematic investigation of how well human examiners perform at identity verification using the same type of images as acquired for automated iris recognition. This paper presents results of an experiment in which examiners consider a pair of iris images to decide if they are either (a) two images of the same eye of the same person, or (b) images of two different eyes, with the two different individuals having the same gender, ethnicity and approximate age. Results suggest that novice examiners can readily achieve accuracy exceeding 90% and can exceed 96% when they judge their decision as ''certain''. Results also suggest that examiners may be able to improve their accuracy with experience.

  • Effects of Iris Surface Curvature on Iris Recognition,
    Joseph Thompson, Patrick Flynn, Kevin W. Bowyer and Hector Santos-Villalobos,
    Biometrics Theory, Applications and Systems (BTAS), Sept 30 - Oct 2, 2013.
    pdf of this paper.
    To focus on objects at various distances, the lens of the eye must change shape to adjust its refractive power. This change in lens shape causes a change in the shape of the iris surface which can be measured by examining the curvature of the iris. This work isolates the variable of iris curvature in the recognition process and shows that differences in iris curvature degrade matching ability. To our knowledge, no other work has examined the effects of varying iris curvature on matching ability. ...

  • Variation in Accuracy of Textured Contact Lens Detection Based on Iris Sensor and Contact Lens Manufacturer,
    James S. Doyle, Kevin W. Bowyer and Patrick J. Flynn,
    Biometrics Theory, Applications and Systems (BTAS) Sept 30 - Oct 2, 2013.
    pdf of this paper.
    ... to date, the experimental results in this area have all been based on the same manufacturer of contact lenses being represented in both the training data and the test data and only one previous work has considered images from more than one iris sensor. Experimental results show that accuracy of textured lens detection can drop dramatically when tested on a manufacturer of lenses not seen in the training data, or when the iris sensor in use varies between the training and test data. These results suggest that the development of a fully general approach to textured lens detection is a problem that still requires attention.

  • A Linear Regression Analysis of the Effects of Age Related Pupil Dilation hChange in Iris Biometrics,
    Estefan Ortiz, Kevin W. Bowyer, and Patrick J. Flynn
    Biometrics Theory, Applications and Systems (BTAS), Sept 30 - Oct 2, 2013.
    pdf of this paper.
    Medical studies have shown that average pupil size decreases linearly throughout adult life. Therefore, on average, the longer the time between acquisition of two images of the same iris, the larger the difference in dilation between the two images. Several studies have shown that increased difference in dilation causes an increase in the false nonmatch rate for iris recognition. Thus, increased difference in pupil dilation is one natural mechanism contributing to an iris template aging effect. We present an experimental analysis of the change in match scores in the context of dilation differences due to aging.

  • Template Aging Phenomenon In Iris Recognition,
    Samuel P. Fenker, Estefan Ortiz and Kevin W. Bowyer,
    IEEE Access 1, 266-274, May 16, 2013.
    link to open access version in IEEE Xplore.
    Biometric template aging is defined as an increase in recognition error rate with increased time since enrollment. It has been believed that template aging does not occur for iris recognition. However, several research groups have recently reported experimental results showing that iris template aging does occur. ...

  • Analysis of Template Aging in Iris Biometrics,
    Samuel P. Fenker and Kevin W. Bowyer,
    IEEE Computer Society Biometrics Workshop, June 2012.
    pdf of this paper.
    It has been widely believed that biometric template aging does not occur for iris biometrics. We compare the match score distribution for short time-lapse iris image pairs, with a mean of approximately one month between the enrollment image and the verification image, to the match score distributions for image pairs with one, two and three years of time lapse. We find clear and consistent evidence of a template aging effect ...

  • Handbook of Iris Recognition,
    Mark J. Burge and Kevin W. Bowyer, editors,
    Springer, 2013.
    publicity flyer. Springer ordering page.
    This is the first book focused solely on iris biometrics. It features chapters on a wide selection of topics, by top researchers from around the world.

  • Automated Classification of Contact Lens Type In Iris Images,
    James S. Doyle, Patrick J. Flynn and Kevin W. Bowyer,
    IAPR International Conference on Biometrics, June 2013.
    pdf of this paper.
    Textured cosmetic lenses have long been known to present a problem for iris recognition. It was once believed that clear, soft contact lenses did not impact iris recognition accuracy. However, it has recently been shown that persons wearing clear, soft contact lenses experience an increased false non-match rate relative to persons not wearing contact lenses. Iris recognition systems need the ability to automatically determine if a person is (a) wearing no contact lens, (b) wearing a clear prescription lens, or (c), wearing a textured cosmetic lens. This work presents results of the first attempt that we are aware of to solve this three-class classification problem. Results show that it is possible to identify with high accuracy (96.5%) the images in which a textured cosmetic contact lens is present, but that correctly distinguishing between no lenses and soft lenses is a challenging problem.

  • The Prediction of Young and Old Subjects From Iris Texture,
    Amanda Sgroi, Kevin W. Bowyer and Patrick J. Flynn,
    IAPR International Conference on Biometrics, June 2013.
    pdf of this paper.
    Researchers have previously studied the prediction of soft biometricÓ attributes such as gender and ethnicity from iris texture images. We present the results of an initial study to predict the relative age of a person from such images. We conclude that is possible to categorize iris images as representing a young or older person at levels of accuracy statistically significantly greater than random chance. This suggests that there may in fact be age-related information available in the iris texture, and motivates further study of this topic.

  • The Impact of Diffuse Illumination on Iris Recognition,
    Amanda Sgroi, Kevin W. Bowyer and Patrick J. Flynn,
    IAPR International Conference on Biometrics, June 2013.
    pdf of this paper.
    Iris illumination typically causes specular highlighting both within the pupil and iris. This lighting variation is intended to be masked in the preprocessing stage. By removing or reducing these specular highlights, it is thought that a more accurate template could be made, improving the matching results. In an attempt to reduce these specular highlights we propose a diffuse illumination system. To determine if iris recognition performance is enhanced by this diffuse illumination system, we examine whether specular highlights were reduced within the pupil and iris, as well as analyze matching results obtained by several iris algorithms.

  • Detection of Contact-Lens-Based Iris Biometric Spoofs Using Stereo Imaging,
    Ken Hughes and Kevin W. Bowyer,
    Hawaii International Conference on System Sciences (HICSS 46), January 7-10, 2013.
    pdf of this paper.
    ... Thus the problem of determining if a person is wearing a cosmetic contact lens is transformed into the problem of classifying the estimated surface shape for the iris region. This is the first approach to analyze iris biometric images in the context of 3D shape.

  • Analysis of Template Aging in Iris Biometrics,
    Samuel P. Fenker and Kevin W. Bowyer,
    CVPR Biometrics Workshop, June 2012.
    pdf of this paper.
    license agreement for image dataset.
    It has been widely believed that biometric template aging does not occur for iris biometrics. We compare the match score distribution for short time-lapse iris image pairs, with a mean of approximately one month between the enrollment image and the verification image, to the match score distributions for image pairs with one, two and three years of time lapse. We find clear and consistent evidence of a template aging effect ...

  • Effects of Dominance and Laterality on Iris Recognition,
    Amanda Sgroi, Kevin W. Bowyer and Patrick Flynn,
    CVPR Biometrics Workshop, June 2012.
    pdf of this paper.
    Eye dominance, the tendency to prefer to process visual input from one eye over the other, is a little discussed topic in iris biometrics. ... In this paper we explore the effects of eye dominance on iris recognition.

  • A Multi-Algorithm Analysis of Three Iris Biometric Sensors,
    Ryan Connaughton, Amanda Sgroi, Kevin W. Bowyer and Patrick J. Flynn,
    IEEE Transactions on Information Forensics and Security 7 (3), 919-931, June 2012.
    pdf of this paper.
    The issue of interoperability between iris sensors is an important topic in large-scale and long-term applications of iris biometric systems. This work compares three commercially available iris sensors and three iris matching systems and investigates the impact of cross-sensor matching on systems performance in comparison to single-sensor performance. Several factors which may impact single-sensor and cross-sensor perofrmance are analyzed ...

  • A Survey of Iris Biometrics Research: 2008-2010,
    Kevin W. Bowyer, Karen P. Hollingsworth and Patrick J. Flynn,
    in Handbook of Iris Recognition, Mark Burge and Kevin W. Bowyer, editors, Springer, 2012.
    pdf of this chapter.

  • Fusion of Face and Iris Biometrics,
    Ryan Connaughton, Kevin W. Bowyer and Patrick Flynn,
    in Handbook of Iris Recognition, Mark Burge and Kevin W. Bowyer, editors, Springer, 2012.
    pdf of this chapter.

  • Template Aging in Iris Biometrics: Evidence of Increased False Reject Rate in ICE 2006,
    Sarah Baker, Kevin W. Bowyer, Patrick J. Flynn and P. Jonathon Phillips,
    in Handbook of Iris Recognition, Mark Burge and Kevin W. Bowyer, editors, Springer, 2012.
    pdf of this chapter.

  • The Results of the NICE.II Iris Biometrics Competition,
    Kevin W. Bowyer,
    Pattern Recognition Letters 33 (8), 965-969, June 2012.
    pdf of this paper.
    ... NICE.II focused on performance in feature extraction and matching. The eight top-performing algorithms from NICE.II are considered, and suggestions are made for lessons that can be drawn from the results.

  • Human and Machine Performance on Periocular Biometrics Under Near-Infrared Light and Visible Light,
    Karen P. Hollingsworth, Shelby S. Darnell, Philip E. Miller, Damon L. Woodard, Kevin W. Bowyer and Patrick J. Flynn,
    IEEE Transactions on Information Forensics and Security 7 (2), 588-601, April 2012.
    pdf of this paper.
    ... Previous periocular research has used either visible light or near-infrared light images, but no prior research has directly compared the two illuminations using images with similar resolution. We conducted an experiment in which volunteers were asked to compare pairs of periocular images. ... We calculated performance of three computer algorithms on the periocular images. Performance for humans and computers was similar.

  • Predicting Ethnicity and Gender from Iris Texture,
    Stephen Lagree and Kevin W. Bowyer,
    IEEE International Conference on Technologies for Homeland Security, November 2011, Boston, MA.
    pdf of this paper.
    Previous researchers have reported success in predicting ethnicity and predicting gender from features of the iris texture. This paper is the first to consider both problems from similar experimental approaches. Contributions of this work include greater accuracy than previous work on predicting ethnicity from iris texture, empirical evidence that suggests that gender prediction is harder than ethnicity prediction, and empirical evidence that ethnicity prediction is more difficult for females than for males.

  • Useful Features for Human Verification in Near-Infrared Periocular Images,
    Karen Hollingsworth, Kevin W. Bowyer and Patrick J. Flynn,
    Image and Vision Computing Journal 29 (11), October 2011, 707-715.
    pdf of this paper.
    ... We conducted two experiments to determine how humans analyze periocular images. In these experiments, we presented pairs of images and asked volunteers to determine whether the two images showed eyes from the same subject or from different subjects. ...
    Reprinted in the Journal of Intelligence Community Research and Development.

  • Dilation Aware Multi-Image Enrollment for Iris Biometrics,
    Estefan Ortiz and Kevin W. Bowyer,
    International Joint Conference on Biometrics (IJCB 2011), October 2011.
    pdf of this paper.
    ... the probability of a false non-match increases when there is a considerable variation in pupil size between the enrolled eye image and the probe eye image. ... Our research examines a strategy to improve system performance by implementing a dilation-aware enrollment phase that chooses eye images based on their respective empirical dilation ratio distribution. ... Our results show that there is a noticeable improvement over the random scenario when pupil dilation is accounted for during the enrollment phase.

  • Predicting Ethnicity and Gender from Iris Texture
    (presentation only),
    Biometrics Consortium Conference (BCC), September 2011, Tampa, Florida.
    pdf of slides.

  • What Surprises Do Identical Twins Have for Identity Science?,
    Kevin W. Bowyer,
    IEEE Computer 44 (7), July 2011, 100-102.
    DOI link to this paper.
    Experiments with biometric datasets from identical twins are helping to shape future research in face and iris recognition.

  • Genetically Identical Irises Have Texture Similarity That Is Not Detected By Iris Biometrics,
    Karen Hollingsworth, Kevin W. Bowyer, Stephen Lagree, Samuel P. Fenker and Patrick J. Flynn,
    Computer Vision and Image Understanding 115, 1493-1502, 2011.
    pdf of this paper.
    As the standard iris biometric algorithm "sees" them, the left and right irises of the same person are as different as irises of unrelated people. Similarly, in terms of iris biometric matching, the eyes of identical twins are as different as irises of unrelated people. The left and right eyes of an individual or the eyes of identical twins are examples of genetically identical irises. In experiments with human observers viewing pairs of iris images acquired using an iris biometric system, we have found that there is recognizable similarity in the left and right irises of an individual and the irises of identical twins. This result suggests that iris texture analysis different from that performance in the standard iris biometric algorithm may be able to answer questions that iris biometrics cannot answer.

  • Improved Iris Recognition Through Fusion of Hamming Distance and Fragile Bit Distance,
    Karen Hollingsworth, Kevin W. Bowyer and Patrick J. Flynn,
    IEEE Transactions on Pattern Analysis and Machine Intelligence 33 (12), December 2011, 2465-2476.
    pdf of this paper.
    ... We find that the locations of fragile bits tend to be consistent across different iris codes of the same eye. We present a metric, called the fragile bit distance, which quantitatively measures the coincidence of the fragile bit patterns in two iris codes. We find that score fusion of fragile bit distances and Hamming distance works better for recognition than Hamming distance alone. To our knowledge, this is the first and only work to use the coincidence of fragile bit locations to improve the accuracy of matches.

  • Experimental Evidence of a Template Aging Effect in Iris Biometrics,
    Sam Fenker and Kevin W. Bowyer,
    IEEE Computer Society Workshop on Applications of Computer Vision, January 2011.
    pdf of this paper.
    license agreement for image dataset.
    Baker et al recently presented the first published evidence of a template aging effect, using images acquired from 2004 through 2008 with an LG 2200 iris imaging system, representing a total of 13 subjects (26 irises). We report on a template aging study involving two different iris recognition algorithms, a larger number of subjects (43), a more modern imaging system (LG 4000), and over a shorter time-lapse (2 years). We also investigate the degree to which the template aging effect may be related to pupil dilation and/or contact lenses.

  • Human Perceptual Categorization of Iris Texture Patterns,
    Louise Stark, Kevin W. Bowyer and Stephen Siena,
    Fourth IEEE International Conference on Biometrics Theory, Applications and Systems (BTAS), September 2010. DOI: 10.1109/BTAS.2010.5634480
    pdf of this paper.
    We report on an experiment in which observers were asked to browse a set of 100 iris images and group them into categories based on similarity of overall texture appearance. Results indicate that there is a natural categorization of iris images into a small number of high-level categories, and then also into sub-categories. ...

  • Degradation of Iris Recognition Performance Due to Non-cosmetic Prescription Contact Lenses,
    Sarah Baker, Amanda Hentz, Kevin W. Bowyer and Patrick J. Flynn,
    Computer Vision and Image Understanding 114 (9), 1030-1044, September 2010.
    pdf of this paper.
    license agreement for image dataset.
    Many iris recognition systems operate under the assumption that non-cosmetic contact lenses have no or minimal effect on iris biometrics performance. ... This is the first study to document degraded iris biometrics performance with non-cosmetic contact lenses.

  • Human Versus Biometric Perception of Iris Texture,
    Presentation only of work done with Karen Hollingsworth, Steve Lagree, Sam Fenker and Patrick J. Flynn,
    Biometrics Consortium Conference (BCC), September 2010, Tampa, FL.
    pdf of slides.

  • Introduction to the Special Issue on Recent Advances In Biometrics,
    Kevin W. Bowyer,
    IEEE Transactions on Systems, Man and Cybernetics - Part A 40 (3), May 2010, 434-436.
    pdf of this paper.
    As with BTAS 07, a biometrics-themed special issue of Systems Man and Cybernetics - Part A was organized following BTAS 08. However, unlike the SMC-A special section drawn from BTAS 07, this special issue had an "open" call for papers, meaning that submissions were not limited to papers presented at BTAS 08. ... A total of 31 submissions were received for the special issue. ... The ten papers that appear in this special issue represent the result of this process. Four of the ten papers appearing in this special issue are revised and extended versions of papers presented in the closing session of the BTAS 08 conference, a session which, by BTAS tradition, is reserved for the submissions that receive the overall best reviews from the conference program committee. The papers in this special issue cover a range of different biometric modalities, including face, ear, iris, signature and multi-modal. In the area of face recognition, there are papers dealing with 2D, 3D, and hand-drawn sketches. Also, the papers in this special issue range from relatively application oriented to relatively theoretical. One common theme is that each paper addresses an important current topic in biometrics research and makes a novel contribution to the state of the art.

  • Factors That Degrade the Match Distribution In Iris Biometrics,
    Kevin W. Bowyer, Sarah E. Baker, Amanda Hentz, Karen Hollingsworth, Tanya Peters and Patrick J. Flynn,
    Identity in the Information Society 2 (3) 327-343, December 2009.
    DOI link. (open access)
    We consider three "accepted truths" about iris biometrics, involving pupil dilation, contact lenses and template aging. We also consider a relatively ignored issue that may arise in system interoperability. Experimental results from our laboratory demonstrate that the three accepted truths are not entirely true, and also that interoperability can involve subtle performance degradation. All four of these problems affect primarily the stability of the match, or authentic, distribution of template comparison scores rather than the non-match, or imposter, distribution of scores. In this sense, these results confirm the security of iris biometrics in an identity verification scenario. We consider how these problems affect the usability and security of iris biometrics in large-scale applications, and suggest possible remedies.

  • Iris Recognition Using Signal-level Fusion of Frames from Video,
    Karen P. Hollingsworth, Tanya Peters, Kevin W. Bowyer and Patrick J. Flynn,
    IEEE Transactions on Information Forensics and Security 4 (4), 837-848, December 2009.
    pdf of this paper.
    DOI link.
    We take advantage of the temporal continuity in an iris video to improve matching performance using signal-level fusion. From multiple frames of a frontal iris video, we create a single average image. ... No published prior work has shown any advantage of the use of video over still images in iris biometrics.

  • Using Fragile Bit Coincidence to Improve Iris Recognition,
    Karen P. Hollingsworth, Kevin W. Bowyer and Patrick J. Flynn,
    Third IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS 09), September 2009, Washington, DC.
    pdf of this paper.
    ... Previous research has shown that iris recognition performance can be improved by making these fragile bits. ... We find that the locations of fragile bits tend to be consistent across different iris codes of the same eye. We present a metrics, called the fragile bit distance, which quantitatively measures the coincidence of the fragile bit patterns in two iris codes. We find that score-fusion of fragile bit distance and Hamming distance works better for recognition than Hamming distance alone. This is the first and only work that we are aware of to use the coincidence of fragile bit locations to improve the accuracy of matches.

  • Stability of the Iris Match Distribution,
    Presentation only of work done with Karen Hollingsworth, Sarah Baker, Amanda Hentz, Tanya Peters and Patrick J. Flynn,
    Biometrics Consortium Conference (BCC), September 2009, Tampa, FL.
    pdf of slides.

  • The ND-IRIS-0405 Iris Image Dataset,
    Kevin W. Bowyer and Patrick J. Flynn,
    Notre Dame CVRL Technical Report.
    pdf of this report.
    The Computer Vision Research Lab at the University of Notre Dame began collecting iris images in the spring semester of 2004. The initial data collections used an LG 2200 iris imaging system for image acquisition. Image datasets acquired in 2004-2005 at Notre Dame with this LG 2200 have been used in the ICE 2005 and ICE 2006 iris biometric evaluations. The ICE 2005 iris image dataset has been distributed to over 100 research groups around the world. The purpose of this document is to describe the content of the ND-IRIS-0405 iris image dataset. This dataset is a superset of the iris image datasets used in ICE 2005 and ICE 2006.

  • FRVT 2006 and ICE 2006 Large-Scale Experimental Results,
    P. Jonathon Phillips, W. Todd Scruggs, Alice O'Toole, Patrick J. Flynn, Kevin W. Bowyer, Cathy L. Schott and Matthew Sharpe,
    IEEE Transactions on Pattern Analysis and Machine Intelligence 32 (5), May 2010, 831-846.
    pdf of this paper.
    DOI link.
    This paper describes the large-scale experimental results from the Face Recognition Vendor Test (FRVT) 2006 and the Iris Challenge Evaluation (ICE) 2006. ...

  • Empirical Evidence for Correct Iris Match Score Degradation With Increased Time Lapse Between Gallery and Probe Images,
    Sarah Baker, Kevin W. Bowyer and Patrick J. Flynn,
    International Conference on Biometrics, June 2009, 1170-1179.
    pdf of this paper.
    license agreement for image dataset.
    We explore the effects of time lapse on iris biometrics using a data set of images with four years time lapse between the earliest and the most recent images of an iris (13 subjects, 26 irises, 1809 total images. We find that the average fractional distance for a match between two images of an iris taken four years apart is significantly larger than the match for images with only a few months time lapse between them. ... To our knowledge, this is the first and only experimental study of iris match scores under long (multi-year) time lapse.

  • Overview of the Multiple Biometric Grand Challenge,
    P. Jonathon Phillips, Patrick J. Flynn, J. Ross Beveridge, W. Todd Scruggs, Alice J. O'Toole, David Bolme, Kevin W. Bowyer, Bruce A. Draper, Geof. H. Givens, Yui Man Lui, Hassan Sahibzada, Joseph A. Scallan, and Samuel Weimer.
    International Conference on Biometrics, June 2009, 705-714.
    pdf of this paper.
    The goal of the Multiple Biometric Grand Challenge (MBGC) is to improve the performance of face and iris recognition technology from samples acquired under unconstrained conditions. The MBGC is organized into three challenge problems. Each challenge problem relaxes the constraints in different directions. ...

  • Image Averaging for Improved Iris Recognition,
    Karen Hollingsworth, Kevin W. Bowyer and Patrick J. Flynn,
    International Conference on Biometrics, June 2009, 1112-1121.
    pdf of this paper.
    We take advantage of the temporal continuity in an iris video to improve matching performance using signal-level fusion. From multiple frames of an iris video, we create a single average image. Our signal-level fusion method performs better that methods based on single still images, and better than previously published multi-gallery score-fusion methods. ...

  • Towards the Next Generation of Iris Biometrics Science,
    Kevin W. Bowyer, Patrick J. Flynn, Karen Hollingsworth, Sarah Baker and Sarah Ring,
    SPIE Newsroom, 2009. DOI link: http://dx.doi.org/10.1117/2.1200904.1595.
    pdf of this paper.
    (A SPIE Newsroom article that gives an overview of the paper and invited talk.)

  • Recent Research Results In Iris Biometrics,
    Karen Hollingsworth, Sarah Baker, Sarah Ring, Kevin W. Bowyer and Patrick J. Flynn,
    SPIE 7306B: Biometric Technology for Human Identification VI, April 2009.
    pdf of this paper.
    ... we have collected more than 100,000 iris images for use in iris biometrics research. Using this data, we have developed a number of techniques for improving recognition rates. These techniques include fragile bit masking, signal-level fusion of iris images, and detecting local distortions in iris texture. Additionally, we have shown that large degrees of dilation and long lapses of time between image acquisitions negatively impact performance.

  • Introduction to the Special Section of Best Papers from the 2007 Biometrics: Theory, Applications and Systems Conference,
    Kevin W. Bowyer,
    IEEE Transactions on Systems, Man and Cybernetics - Part A, 39 (1), January 2009, 2-3.
    pdf of this paper.
    DOI link.
    ... Over 100 papers were submitted to BTAS 07. ... The final result of this process is the set of five papers that appear in this special section. We are particularly fortunate in the way that the five papers in this special section illustrate the breadth of activities in current biometrics research. Face, fingerprint, iris, voice, handwriting, and multimodal biometrics are all represented. ...

  • Pupil Dilation Degrades Iris Biometric Performance,
    Karen Hollingsworth, Kevin W. Bowyer and Patrick J. Flynn,
    Computer Vision and Image Understanding, 113 (1), January 2009, 150-157.
    pdf of this paper.
    DOI link.
    ... We found that when the degree of dilation is similar at enrollment and recognition, comparisons involving highly dilated pupils result in worse recognition performance than comparisons involving constricted pupils. We also found that when the matched images have similarly highly dilated pupils, the mean Hamming distance of the match distribution increases and the mean Hamming distance of the non-match distribution decreases, bringing the distributions closer together from both directions. We further found that when matching enrollment and recognition images of the same person, larger differences in pupil dilation yield higher template dissimilarities, and so a greater chance of a false non-match. ...
    Our research group is part of the Multiple Biometric Grand Challenge and Iris Challenge Evaluation support teams.

  • The Best Bits In an Iris Code,
    Karen Hollingsworth, Kevin W. Bowyer and Patrick J. Flynn,
    IEEE Transactions on Pattern Analysis and Machine Intelligence 31 (6), 964-973, June 2009.
    pdf of this paper.
    ... The fractional Hamming distance weights all bits in an iris code equally. However, not all the bits in an iris code are equally useful. Our research is the first to present experiments documenting that some bits are more consistent than others. ... The inconsistencies are largely due to the coarse quantization of the phase response. Masking iris code bits corresponding to complex filter responses near the axes of the complex plane improves the separation between the match and nonmatch Hamming distance distributions.
    Our research group is part of the Multiple Biometric Grand Challenge and Iris Challenge Evaluation support teams.

  • Detection of Iris Texture Distortions By Analyzing Iris Code Matching Results,
    Sarah Ring and Kevin W. Bowyer,
    Second IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS 08), September 2008, Washington, DC.
    pdf of this paper.
    Previous work in iris biometrics attempts to cope with occlusion by eyelids / eyelashes and with specular highlights through improved segmentation of the iris region. Our approach assumes that some local distortions of the iris texture are not detected at the segmentation stage, and that these generate corresponding regions of local distortion in the iris code derived from the image. We introduce an approach to detect such regions of local distortion in the iris code through analysis of the iris code matching results. We know of no previous work that attempts to detect distortions of iris texture through analyzing the iris code matching results.

  • The Iris Challenge Evaluation 2005,
    P. Jonathon Phillips, Kevin W. Bowyer and Patrick J. Flynn, Xiaomei Liu and W. Todd Scruggs,
    Second IEEE International Conferenece on Biometrics: Theory, Applications and Systems (BTAS 08), September 2008, Washington, DC.
    DOI link.

  • Image Understanding for Iris Biometrics: A Survey,
    Kevin W. Bowyer, Karen Hollingsworth and Patrick J. Flynn,
    Computer Vision and Image Understanding, 110(2), 281-307, May 2008.
    DOI link.
    ... Most research publications can be categorized as making their primary contribution to one of the four major modules in iris biometrics: image acquisition, iris segmentation, texture analysis and matching of texture representations. Other important research includes experimental evaluations, image databases, applications and systems, and medical conditions that may affect the iris. ...
    Our research group is part of the Multiple Biometric Grand Challenge and Iris Challenge Evaluation support teams.

  • Learning to Predict Gender from Irises,
    Vince Thomas, Nitesh V. Chawla, Kevin W. Bowyer and Patrick J. Flynn,
    First IEEE International Conference on Biometrics: Theory, Applications, and Systems (BTAS 07), September 2007.
    pdf of this paper.
    This paper employs machine learning techniques to develop models that predict gender based on the iris texture features. ...

  • Guest Editorial: Introduction to the Special Issue on Recent Advances in Biometric Systems,
    Kevin W. Bowyer, Venu Govindaraju and Nalini Ratha,
    IEEE Transactions on Systems, Man and Cybernetics - B 37 (5), October 2007.
    pdf of this paper.
    We are pleased to present 14 papers in this special issue devoted to recent advances in biometric systems. ...

  • Comment on the CASIA version 1.0 Iris Dataset,
    P. Jonathon Phillips, Kevin W. Bowyer and Patrick J. Flynn,
    IEEE Transactions on Pattern Analysis and Machine Intelligence 29 (10), October 2007.
    pdf of this paper.
    We note that the images in the CASIA version 1.0 iris dataset have been edited so that the pupil area is replaced by a circular region of uniform intensity. We recommend that this dataset is no longer used in iris biometrics research ...

  • Multi-modal Biometrics: An Overview,
    Kevin W. Bowyer, et al,
    Second Workshop on Multi-Modal User Authentication (MMUA 2006), May 2006, Toulouse, France.
    pdf of this paper.
    The topic of multi-modal biometrics has attracted strong interest in recent years. This paper categorizes approaches to multi-modal biometrics based on the biometric source, the type of sensing used, and the depth of collaborative interaction in the processing. This paper also attempts to identify some of the challenges and issues that confront research in multi-modal biometrics.
    This paper represents the invited talk given to open the first day of the workshop.

  • Experiments With an Improved Iris Segmentation Algorithm,
    Xiaomei Liu, Kevin W. Bowyer, and Patrick J. Flynn,
    Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID), October 2005, New York, 118-123.
    pdf of this paper.
    ... We have also developed and implemented an improved iris segmentation and eyelid detection stage of the algorithm, and experimentally verified the improvement in recognition performance using the collected dataset. Compared to Masek's original segmentation approach, our improved segmentation algorithm leads to an increase of over 6% in the rank-one recognition rate.

Home

Research

Teaching

Professional

Personal