ORNL biometric eye model for iris recognition

Hector J. Santos-Villalobos, Del R. Barstow, Mahmut Karakaya, Chris B. Boehnen, Edward Chaum

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Citations (Scopus)

Abstract

Iris recognition has been proven to be an accurate and reliable biometric. However, the recognition of non-ideal iris images such as off angle images is still an unsolved problem. We propose a new biometric targeted eye model and a method to reconstruct the off-axis eye to its frontal view allowing for recognition using existing methods and algorithms. This allows for existing enterprise level algorithms and approaches to be largely unmodified by using our work as a pre-processor to improve performance. In addition, we describe the 'Limbus effect' and its importance for an accurate segmentation of off-axis irides. Our method uses an anatomically accurate human eye model and ray-tracing techniques to compute a transformation function, which reconstructs the iris to its frontal, non-refracted state. Then, the same eye model is used to render a frontal view of the reconstructed iris. The proposed method is fully described and results from synthetic data are shown to establish an upper limit on performance improvement and establish the importance of the proposed approach over traditional linear elliptical unwrapping methods. Our results with synthetic data demonstrate the ability to perform an accurate iris recognition with an image taken as much as 70 degrees off-axis.

Original languageEnglish (US)
Title of host publication2012 IEEE 5th International Conference on Biometrics
Subtitle of host publicationTheory, Applications and Systems, BTAS 2012
Pages176-182
Number of pages7
DOIs
StatePublished - Dec 1 2012
Event2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012 - Arlington, VA, United States
Duration: Sep 23 2012Sep 27 2012

Other

Other2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012
CountryUnited States
CityArlington, VA
Period9/23/129/27/12

Fingerprint

Biometrics
Ray tracing
Industry

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Biomedical Engineering

Cite this

Santos-Villalobos, H. J., Barstow, D. R., Karakaya, M., Boehnen, C. B., & Chaum, E. (2012). ORNL biometric eye model for iris recognition. In 2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012 (pp. 176-182). [6374574] https://doi.org/10.1109/BTAS.2012.6374574

ORNL biometric eye model for iris recognition. / Santos-Villalobos, Hector J.; Barstow, Del R.; Karakaya, Mahmut; Boehnen, Chris B.; Chaum, Edward.

2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012. 2012. p. 176-182 6374574.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Santos-Villalobos, HJ, Barstow, DR, Karakaya, M, Boehnen, CB & Chaum, E 2012, ORNL biometric eye model for iris recognition. in 2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012., 6374574, pp. 176-182, 2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012, Arlington, VA, United States, 9/23/12. https://doi.org/10.1109/BTAS.2012.6374574
Santos-Villalobos HJ, Barstow DR, Karakaya M, Boehnen CB, Chaum E. ORNL biometric eye model for iris recognition. In 2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012. 2012. p. 176-182. 6374574 https://doi.org/10.1109/BTAS.2012.6374574
Santos-Villalobos, Hector J. ; Barstow, Del R. ; Karakaya, Mahmut ; Boehnen, Chris B. ; Chaum, Edward. / ORNL biometric eye model for iris recognition. 2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012. 2012. pp. 176-182
@inproceedings{d41b6ba62e31490bad1f0faec6c8955a,
title = "ORNL biometric eye model for iris recognition",
abstract = "Iris recognition has been proven to be an accurate and reliable biometric. However, the recognition of non-ideal iris images such as off angle images is still an unsolved problem. We propose a new biometric targeted eye model and a method to reconstruct the off-axis eye to its frontal view allowing for recognition using existing methods and algorithms. This allows for existing enterprise level algorithms and approaches to be largely unmodified by using our work as a pre-processor to improve performance. In addition, we describe the 'Limbus effect' and its importance for an accurate segmentation of off-axis irides. Our method uses an anatomically accurate human eye model and ray-tracing techniques to compute a transformation function, which reconstructs the iris to its frontal, non-refracted state. Then, the same eye model is used to render a frontal view of the reconstructed iris. The proposed method is fully described and results from synthetic data are shown to establish an upper limit on performance improvement and establish the importance of the proposed approach over traditional linear elliptical unwrapping methods. Our results with synthetic data demonstrate the ability to perform an accurate iris recognition with an image taken as much as 70 degrees off-axis.",
author = "Santos-Villalobos, {Hector J.} and Barstow, {Del R.} and Mahmut Karakaya and Boehnen, {Chris B.} and Edward Chaum",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/BTAS.2012.6374574",
language = "English (US)",
isbn = "9781467313841",
pages = "176--182",
booktitle = "2012 IEEE 5th International Conference on Biometrics",

}

TY - GEN

T1 - ORNL biometric eye model for iris recognition

AU - Santos-Villalobos, Hector J.

AU - Barstow, Del R.

AU - Karakaya, Mahmut

AU - Boehnen, Chris B.

AU - Chaum, Edward

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Iris recognition has been proven to be an accurate and reliable biometric. However, the recognition of non-ideal iris images such as off angle images is still an unsolved problem. We propose a new biometric targeted eye model and a method to reconstruct the off-axis eye to its frontal view allowing for recognition using existing methods and algorithms. This allows for existing enterprise level algorithms and approaches to be largely unmodified by using our work as a pre-processor to improve performance. In addition, we describe the 'Limbus effect' and its importance for an accurate segmentation of off-axis irides. Our method uses an anatomically accurate human eye model and ray-tracing techniques to compute a transformation function, which reconstructs the iris to its frontal, non-refracted state. Then, the same eye model is used to render a frontal view of the reconstructed iris. The proposed method is fully described and results from synthetic data are shown to establish an upper limit on performance improvement and establish the importance of the proposed approach over traditional linear elliptical unwrapping methods. Our results with synthetic data demonstrate the ability to perform an accurate iris recognition with an image taken as much as 70 degrees off-axis.

AB - Iris recognition has been proven to be an accurate and reliable biometric. However, the recognition of non-ideal iris images such as off angle images is still an unsolved problem. We propose a new biometric targeted eye model and a method to reconstruct the off-axis eye to its frontal view allowing for recognition using existing methods and algorithms. This allows for existing enterprise level algorithms and approaches to be largely unmodified by using our work as a pre-processor to improve performance. In addition, we describe the 'Limbus effect' and its importance for an accurate segmentation of off-axis irides. Our method uses an anatomically accurate human eye model and ray-tracing techniques to compute a transformation function, which reconstructs the iris to its frontal, non-refracted state. Then, the same eye model is used to render a frontal view of the reconstructed iris. The proposed method is fully described and results from synthetic data are shown to establish an upper limit on performance improvement and establish the importance of the proposed approach over traditional linear elliptical unwrapping methods. Our results with synthetic data demonstrate the ability to perform an accurate iris recognition with an image taken as much as 70 degrees off-axis.

UR - http://www.scopus.com/inward/record.url?scp=84871989854&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871989854&partnerID=8YFLogxK

U2 - 10.1109/BTAS.2012.6374574

DO - 10.1109/BTAS.2012.6374574

M3 - Conference contribution

SN - 9781467313841

SP - 176

EP - 182

BT - 2012 IEEE 5th International Conference on Biometrics

ER -