Presentation is loading. Please wait.

Presentation is loading. Please wait.

Uba Anydiewu, Shane Bilinski, Luis Garcia, Lauren Ragland, Debracca Thornton, Joe Tubesing, Kevin Chan, Steve Elliott, and Ben Petry EXAMINING INTRA-VISIT.

Similar presentations


Presentation on theme: "Uba Anydiewu, Shane Bilinski, Luis Garcia, Lauren Ragland, Debracca Thornton, Joe Tubesing, Kevin Chan, Steve Elliott, and Ben Petry EXAMINING INTRA-VISIT."— Presentation transcript:

1 Uba Anydiewu, Shane Bilinski, Luis Garcia, Lauren Ragland, Debracca Thornton, Joe Tubesing, Kevin Chan, Steve Elliott, and Ben Petry EXAMINING INTRA-VISIT IRIS STABILITY (VISIT 2)

2 Biometrics is defined as any automatically measurable, robust, and distinctive physical characteristic or personal trait that can be used to identify an individual or verify the claimed identity of an individual” [1] WHAT IS BIOMETRICS?

3 Physiological Face Iris Fingerprints Behavioral Keystroke Signature Gait BIOMETRICS – PHYSIOLOGICAL / BEHAVIORAL

4 Improves Security Ease of use Reliability BIOMETRICS

5 Iris is the colored part of the eye in the center of the sclera [2] The iris is unique and distinct from others [2] IRIS – WHAT IS IT?

6 Unique, stable over time [2] Recognition is a faster and less intrusive method for biometrics. Fingerprinting and hand geometry require physical contact. Stability affected by other sources. [2] Lighting Sickness Drug consumption Intoxication IRIS

7 The iris image is first captured. Localized for further feature extraction. Segmented into binary code. Iris is then compared to a template in the system to see if a match can be found [2]. HOW IRIS RECOGNITION WORKS

8 The iris is assumed to remain stable over time. This means that the iris should not change its unique characteristics [2]. STABILITY OF THE IRIS

9 The iris should provide consistent genuine or impostor scores. Stability is the resiliency to variation of a biometric modality over a determined time interval or the resiliency to change given certain environmental factors [6]. STABILITY - PERFORMANCE

10 IRIS STABILITY OVER TIME (AGING) There is debate as to whether or not the iris changes over time due to aging. Iris aging is a definitive change in the iris texture pattern due to human aging. Evidence has shown that there is no change in the iris over time over time due to aging.

11 What is it? Refers to changes in the enrolled template over time. How does it differ from iris aging? Iris aging = Human eye Template aging = Enrolled eye image TEMPLATE AGING

12 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. [4] TEMPLATE VS IRIS AGING

13 Trend analysis – Practice of collecting information and attempting to spot a pattern. ROC Curve – Receiver operating characteristic, a graphical plot that illustrates the performance of a binary classifier system. DET Curve – Detection error tradeoff, a graphical plot of error rates for binary classification systems. Hamming Distance – found between two strings of equal length and determines how different they are. WAYS OF ANALYZING BIOMETRIC PERFORMANCE

14 Genuine – Score when compared against a proven match Impostor – Score when compared against a proven non- match FNMR – False Non-Match Rate ISO Standard (ISO 19795, clause 4.6.3) FMR – False Match Rate ISO Standard (ISO 19765, clause 4.6.4) DEFINITIONS

15 6.3 False non-match rate FNMR proportion of genuine attempt samples falsely declared not to match the template of the same characteristic from the same user supplying the sample Note 1 to entry: The measured/observed false non-match rate is distinct from the predicted/expected false non- match rate (the former may be used to estimate the latter). 6.4 False match rate FMR Proportion of zero-effort impostor attempt samples falsely declared to match the compared non-self template Note 1 to entry: The measured/observed false match rate is distinct from the predicted/expected false match rate (the former may be used to estimate the latter). DEFINITIONS: ISO 19795-4

16 RESULTS

17 VISIT 2 AGE GROUPS

18 VISIT 2 GENDER

19 VISIT 2 – SELF DISCLOSED ETHNICITY

20 VISIT 1NHDFP Group 1601.3220.517 Group 2600.2320.893 Group 3600.1420.932 Group 4602.4120.300 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.

21 CONCLUSIONS

22 Future research Spans of 30 minutes or more Spans of 1 day or more Replicate with freshly collected data FUTURE RESEARCH

23 [1] Woodward Jr, J. D., Horn, C., Gatune, J., & Thomas, A. (2003). Biometrics: A look at facial recognition. RAND Corp, Santa Monica, CA. [2] Daugman, J. (2009). How Iris Recognition Works. The Essential Guide to Image Processing, 14(1), 715–739. doi:10.1016/B978-0-12-374457-9.00025-1 [3] Paone, J., & Flynn, P. J. (2011). On the consistency of the biometric menagerie for irises and iris matchers. 2011 IEEE International Workshop on Information Forensics and Security, WIFS 2011. doi:10.1109/WIFS.2011.6123158 [4] Fenker, S. P., & Bowyer, K. W. (2011). Experimental evidence of a template aging effect in iris biometrics. 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011, 232–239. doi:10.1109/WACV.2011.5711508 [5] “Information technology – Biometric performance testing and reporting - Part 1: Principles and framework.” [Online]. Available: https://www.iso.org/obp/ui/#iso:std:iso-iec:19795:-1:ed-1:v1:en. ;Accessed: 04-Feb-2015]. [6] K. O’Connor, “Examination of stability in fingerprint recognition across force levels,” p. 89, 2013. REFERENCES


Download ppt "Uba Anydiewu, Shane Bilinski, Luis Garcia, Lauren Ragland, Debracca Thornton, Joe Tubesing, Kevin Chan, Steve Elliott, and Ben Petry EXAMINING INTRA-VISIT."

Similar presentations


Ads by Google