p st listed under 35 Sinjini Mitra, Marios Savvides, Gaussian Mixture Models Based on M YW(b) by ayS. the Frequency Spectra for Human Identification and Illumination Classification, 4th IEEE Workshop on Automatic Identification (21) Appl. No.: 13/020,805 Advanced Technologies, 2005, Buffalo, NY, USA Oct. 17-18, 2005, 245-250. (22) Filed: Feb. 3, 2011 pp (Continued) (65) Prior Publication Data Primary Examiner — Michael Osinski US 2012/O200725A1 Aug. 9, 2012 (74) Attorney, Agent, or Firm — Andrew V. Smith

A recent survey of iris biometric research from its inception through 2007, roughly 15 years of research, lists approximately 180 publications. This new survey is intended to update the previous one, and covers iris biometrics research over the period of roughly 2008-2010. Research in iris biometrics has expanded so much that although covering only 3 years and intentionally being selective about coverage, this new survey lists a larger number of references than the inception through 2007 survey.

High-quality periocular images have sufficient variability between people that they can be used for automated recognition. However, there are no standards for training people to compare periocular images in a forensic context. Potential methods for training people to compare eyebrow images are investigated in this article. Pairs of images were presented to volunteers who decided whether the images showed the same person or different people. A control group with minimal instruction and no training responded with 87.6% accuracy. A second group viewed 100 training pairs before the test and achieved 94.2% accuracy. A third group rated specific features in the images and had 0.1% improvement over the second group. Experimental results show that actively comparing at least thirty training images and receiving immediate feedback improves trainees' performance six to seven percent. If a quantitative quality score is needed, a linear combination of similarity ratings on different features may be used.

Prior research has shown that manually-segmented eyebrows can be used for recognition purposes. However, eyebrow recognition is not as useful without an automated segmentation algorithm. We propose a method to automatically outline the eyebrows in a face using active shape models. We train several models using the images from the Face Recognition Grand Challenge and find that including more landmark points around the eyebrows and including the eyes in the model are beneficial. Our eyebrow active shape model gives a 38.6% improvement over eyebrow segmentation obtained using an open-source face active shape model. When comparing the automatically segmented regions with manual segmentation, we achieve 87% true overlap score with a 12% false overlap score.

The most common iris biometric algorithm represents the texture of an iris using a binary iris code. Not all bits in an iris code are equally consistent. A bit is deemed fragile if its value changes across iris codes created from different images of the same iris. Previous research has shown that iris recognition performance can be improved by masking these fragile bits. Rather than ignoring fragile bits completely, we consider what beneficial information can be obtained from the 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 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 distance 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.

The periocular region is the part of the face immediately surrounding the eye, and researchers have recently begun to investigate how to use the periocular region for recognition. Understanding how humans recognize faces helped computer vision researchers develop algorithms for face recognition. Likewise, understanding how humans analyze periocular images could benefit researchers developing algorithms for periocular recognition. 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. In the first experiment, subjects were paired randomly to create different-subject queries. Our volunteers correctly determined the relationship between the two images in 92% of the queries. In the second experiment, we considered multiple factors in forming different-subject pairs; queries were formed from pairs of subjects with the same gender and race, and with similar eye color, makeup, eyelash length, and eye occlusion. In addition, we limited the amount of time volunteers could view a query pair. On this harder experiment, the correct verification rate was 79%. We asked volunteers to describe what features in the images were helpful to them in making their decisions. In both experiments, eyelashes were reported to be the most helpful feature.

Periocular biometrics is the recognition of individuals based on the appearance of the region around the eye. Periocular recognition may be useful in applications where it is difficult to obtain a clear picture of an iris for iris biometrics, or a complete picture of a face for face biometrics. Previous periocular research has used either visible-light (VL) or near-infrared (NIR) 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. Some pairs showed images taken in VL, and some showed images taken in NIR light. Participants labeled each pair as belonging to the same person or to different people. Untrained participants with limited viewing times correctly classified VL image pairs with 88% accuracy, and NIR image pairs with 79% accuracy. For comparison, we presented pairs of iris images from the same subjects. In addition, we investigated differences between performance on light and dark eyes and relative helpfulness of various features in the periocular region under different illuminations. We calculated performance of three computer algorithms on the periocular images. Performance for humans and computers was similar.

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 in the irises of identical twins. This result suggests that iris texture analysis different from that performed in the standard iris biometric algorithm may be able to answer questions that iris biometrics cannot answer.

The periocular region is the part of the face immediately surrounding the eye, and researchers have recently begun to investigate how to use the periocular region for recognition. Understanding how humans recognize faces helped computer vision researchers develop algorithms for face recognition. Likewise, understanding how humans analyze periocular images could benefit researchers developing algorithms for periocular recognition. We presented pairs of periocular images to testers and asked them to determine whether the two images were from the same person or from different people. Our testers correctly determined the relationship between the two images in over 90% of the queries. We asked them to describe what features in the images were helpful to them in making their decisions. We found that eyelashes, tear ducts, shape of the eye, and eyelids were used most frequently in determining whether two images were from the same person. The outer corner of the eye and the shape of the eye were used a higher proportion of the time for incorrect responses than they were for correct responses, suggesting that those two features are not as useful.

Iris biometrics is used in a number of different applications, such as frequent flyer programs, identification of prisoners, and border control in the United Arab Emirates. However, governments interested in using iris biometrics have still found difficulties using it on large populations. Further improvements in iris recognition are required in order to enable this technology to be used in more settings.In this dissertation, we describe three methods of reducing error rates for iris biometrics. We define and employ a metric called the fragile bit distance which uses the locations of less stable bits in an iris template to improve performance. We also investigate signal fusion of multiple frames in an iris video to achieve better recognition performance than is possible using single still images. Third, we present a study of what features are useful for identification in the periocular region. Periocular biometrics is still an emerging field of research, but we anticipate that fusing periocular information with iris information will result in a more robust biometric system. A final contribution of this work is a study of how iris biometrics performs on twins. Our experiments confirm prior claims that iris biometrics is capable of differentiating between twins. However, we additionally show that there is texture information in the iris that is not encoded by traditional iris biometrics systems. Our experiments suggest that human examination of pairs of iris images for forensic purposes may be feasible. Our results also suggest that development of different approaches to automated iris image analysis may be useful.

Prior research has shown that the textural detail of the iris is sufficiently distinctive to distinguish identical twin siblings. However, no research has addressed the question of whether twins' irises are sufficiently similar in some sense to correctly determine that two irises are from twins. We conducted a human classification study in which participants were asked to label pairs of iris images as “twins” or “unrelated”. Participants were given three seconds to view each pair of images. We found that untrained humans can classify pairs of twins with more than 81% accuracy using the appearance of the iris alone, without any proximal image content such as eyelashes, eyelids, or tear duct visible. When expressing confident judgment, they are over 92% accurate.

Iris biometric systems apply filters to iris images to extract information about iris texture. Daugman's approach maps the filter output to a binary iris code. The fractional Hamming distance between two iris codes is computed and decisions about the identity of a person are based on the computed distance. 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. Different regions of the iris are compared to evaluate their relative consistency, and contrary to some previous research, we find that the middle bands of the iris are more consistent than the inner bands. The inconsistent-bit phenomenon is evident across genders and different filter types. Possible causes of inconsistencies, such as segmentation, alignment issues, and different filters are investigated. 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.

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. For comparison, we reimplement three score-level fusion methods (Ma, Krichen, and Schmid). We find that our signal-level fusion of N images performs better than Ma's or Krichen's score-level fusion methods of N Hamming distance scores. Our signal-level fusion performs comparably to Schmid's log-likelihood method of score-level fusion, and our method achieves this performance using less computation time. We compare our signal fusion method with another new method: a multigallery, multiprobe method involving score-level fusion of N 2 Hamming distances. The multigallery, multiprobe score fusion has slightly better recognition performance, while the signal fusion has significant advantages in memory and computation requirements. No published prior work has shown any advantage of the use of video over still images in iris biometrics.

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 than methods based on single still images, and better than previously published multi-gallery score-fusion methods. We compare our signal fusion method with another new method: a multi-gallery, multi-probe score fusion method. Between these two new methods, the multi-gallery, multi-probe score fusion has slightly better recognition performance, while the signal fusion has significant advantages in memory and computation requirements.

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.

Many security applications require accurate identification of people, and research has shown that iris biometrics can be a powerful identification tool. However, in order for iris biometrics to be used on larger populations, error rates in the iris biometrics algorithms must be as low as possible. Furthermore, these algorithms need to be tested in a number of different environments and configurations. In order to facilitate such testing, 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.

The most common iris biometric algorithm represents the texture of an iris using a binary iris code. Not all bits in an iris code are of equal value. A bit is deemed fragile if it varies in value across iris codes created from different images of the same iris. Previous research has shown that iris recognition performance can be improved by masking these fragile bits. Rather than ignoring fragile bits completely, we consider what beneficial information can be obtained from the 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 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 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.

Previous research has assumed that all parts of an iris code are equally valuable. Alternatively, some researchers claim that parts of the iris are more valuable, but they still use the same portions of the iris for all subjects. Our research, presented originally, is the first and only work to show experimentally that some bits in the iris code are less reliable than others, and these patterns of fragile bits vary on a subject by subject basis. This paper extends the work presented, answering questions such as "how does a different filter affect the patterns of fragile bits?" and "what causes outliers in these distributions?" We present a modification to our iris biometric system that masks fragile bits and significantly shifts the match distribution away from the non-match distribution.