Kevin W. Bowyer - Publications With Undergrad Co-Authors

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 (2011), 1493-1502. http://dx.doi.org/10.1016/j.cviu.2011.06.010

Ethnicity Prediction Based on Iris Texture Features,
Stephen Lagree and Kevin W. Bowyer,
22nd Midwest Artificial Intelligence and Cognitive Science Conference (MAICS 2011), April 2011, Cincinnati, Ohio.

Experimental evidence of a template aging effect in iris biometrics,
Sam Fenker and Kevin W. Bowyer,
Workshop on Applications of Computer Vision, January 2011.
pdf of this paper.
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,
Biometrics Theory, Applications and Systems (BTAS), to appear.
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.
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 detection of similarity in left and right irises,
Kevin W. Bowyer, Steve Lagree and Sam Fenker,
IEEE International Carnahan Conference on Security Technology, October 2010, to appear.
pdf of this paper.
The iris codes for the left and right iris of a person have previously been reported to be uncorrelated. We replicate this result using images from 327 persons from the iris image dataset used in the Iris Challenge Evaluations. The same images are then used in an experiment in which subjects view a left and a right iris image, and judge whether they are correctly paired by similarity of iris texture. Subjects are able to distinguish between iris images belonging to the same person versus belonging to different persons with over 86% accuracy overall, and over 93% accuracy when they judge their decision as confident.

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, 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.

Contact Lenses: Handle With Care for Iris Recognition,
Sarah Baker, Amanda Hentz, Kevin W. Bowyer and Patrick J. Flynn,
Biometrics: Theory, Applications and Systems (BTAS 09), September 2009, Washington, DC.
pdf of this paper (not final version).

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.

Detection of Iris Texture Distortions By Analyzing Iris Code Matching Results,
Sarah Ring and Kevin W. Bowyer,
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.

Learning to Predict Gender from Irises,
Vince Thomas, Nitesh V. Chawla, Kevin W. Bowyer and Patrick J. Flynn,
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. ...