EXAMINING INTRA-VISIT IRIS STABILITY (VISIT 1) Bo Brown, Jing Guan, Vince Sipocz, Aidan Chamberlain, Brandon Cox, Preston Flint, Eric Hollensbe, Brandon.

EXAMINING INTRA-VISIT IRIS STABILITY

(VISIT 1) Bo Brown, Jing Guan, Vince Sipocz, Aidan

Chamberlain, Brandon Cox, Preston Flint, Eric Hollensbe, Brandon Krieg, David Manfred, Zack Tauer,

Kevin Chan, Steve Elliott, and Ben Petry

• Automatic recognition of individuals based on their distinguishing biological and behavioral features. [1]

• Types:– Face, voice, fingerprint, and iris.– Can be physiological and behavioral.

BIOMETRICS

IRIS ASSUMPTIONS

• Unique, stable over time [2]• Recognition is a faster and less intrusive

method for biometrics• Performance could be attributed to other

issues, not the biological stability of the iris• Pupil dilation could be affected by a

number of factors

•The iris is the colored portion of the eye. [3]

•The outer bounds are defined by the white sclera.

•The inner bounds are defined by the black pupil.

STUCTURE OF THE EYE

PROBLEM STATEMENT• Is the iris stable over time?

• Specifically:• Does the stability score index change across four

groupings of three images taken in succession in one visit within a day?

• Data collection began on 11 June 2010 and lasted for 1 year and 2 days (2010-06-11Z/P1Y0M0W2D).

• The time scope of interest for this report is in the day range.

• The collection period of interest for this analysis began on 11 April 2013 and lasted for four weeks and 1 day (2013-04-11Z/P0Y0M4W1D).

COLLECTION PERIOD

• Aging definition [4]

• To make old; cause to grow or seem old

• To bring to maturity or a state fit for use

AGING

• A template aging effect occurs when the quality of the match between an enrolled biometric sample and a sample to be verified degrade with the increased elapsed time between two samples.

• Algorithm to find a match finds a difference causing the match scores to decrease.

• Iris aging is a definite change in the iris texture pattern that occurs from human aging.

TEMPLATE VS IRIS AGING

• Definition: The tendency to remain accurate over time [3]

• Research focus: Examining stability of the iris over time

• Action plan:

• Reviewed time, and issues on the dynamics of time

• Examined template aging vs. biological aging

• Developed a methodology

• Completed the data analysis

• Results

STABILITY

• [6]

STABILITY SCORE INDEX

• Debate in the research community about the stability of the iris – and the iris template.

• Although the iris is stable over time [4], the iris template can change.

• Changes that can affect stability include, but are not limited to:

•The presence of visual aids (like glasses or contacts)

•The occlusion of the iris caused by the eyelids

STABILITY OF THE IRIS

• Data were collected as part of a multimodal study, at the International Center for Biometric Research

• Data were collected in a controlled lab environment• Data were subject to ground truth, i.e. – checked for

errors and consistency

DATA

RESULTS

VISIT 1 AGE GROUPS

VISIT 1 GENDER

VISIT 1 – SELF DISCLOSED ETHNICITY

VISIT 1 N H DF P

Group 1 60 0.08 2 0.960

Group 2 60 0.89 2 0.642

Group 3 60 1.70 2 0.428

Group 4 60 0.45 2 0.800

RESULTS

There was not a statistically significant difference between the median of the groupings, as indicated in the summary table. For this data, we can conclude that the iris is stable in this visit.

•The results show that the iris is stable over a collection period of less then fifteen minutes, as theorized by Daugman [1][4].

CONTRIBUTION TO THE FIELD

•Testing the stability of the iris over longer periods of time (days, weeks, etc.)

•Continued replication with similar data

FUTURE WORK

[1] History of Biometrics. (n.d.). Retrieved February 20, 2015, from http://www.biometricupdate.com/201501/history-of-biometrics

[2] Structure of the Eye, http://www.uofmhealth.org/health-library/tp9807

[3] Daugman, J. (2004). How iris recognition works. Circuits and Systems for Video Technology, IEEE Transactions on, 14(1), 21-30.

[4] Daugman, J. (2006). Probing the uniqueness and randomness of IrisCodes: Results from 200 billion iris pair comparisons. Proceedings of the IEEE, 94(11), 1927-1935

[5] Doddington, G., Liggett, W., Martin, A., Przybocki, M., & Reynolds, D. (1998, November). Sheep, goats, lambs and wolves: an analysis of individual differences in speaker recognition performance. In the International Conference on Spoken Language Processing (ICSLP), Sydney.

[6] O'Connor, K. J. (2013). Examination of stability in fingerprint recognition across force levels, MS. Thesis, Purdue University, West Lafayette, IN.

BIBLIOGRAPHY