Journal of Korea Multimedia Society (한국멀티미디어학회논문지)

Korea Multimedia Society (한국멀티미디어학회)
권호 표지

A Study on the Restoration of a Low-Resoltuion Iris Image into a High-Resolution One Based on Multiple Multi-Layered Perceptrons

다중 다층 퍼셉트론을 이용한 저해상도 홍채 영상의 고해상도 복원 연구

  • 신광용 (동국대학교 전자전기공학부) ;
  • 강병준 (한국전자통신연구원 휴먼인식기술연구팀) ;
  • 박강령 (동국대학교 전자전기공학부) ;
  • 신재호 (동국대학교 전자전기공학부)
  • Received : 2009.11.06
  • Accepted : 2009.12.17
  • Published : 2010.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Iris recognition uses a unique iris pattern of user to identify person. In order to enhance the performance of iris recognition, it is reported that the diameter of iris region should be greater than 200 pixels in the captured iris image. So, the previous iris system used zoom lens camera, which can increase the size and cost of system. To overcome these problems, we propose a new method of enhancing the accuracy of iris recognition on low-resolution iris images which are captured without a zoom lens. This research is novel in the following two ways compared to previous works. First, this research is the first one to analyze the performance degradation of iris recognition according to the decrease of the image resolution by excluding other factors such as image blurring and the occlusion of eyelid and eyelash. Second, in order to restore a high-resolution iris image from single low-resolution one, we propose a new method based on multiple multi-layered perceptrons (MLPs) which are trained according to the edge direction of iris patterns. From that, the accuracy of iris recognition with the restored images was much enhanced. Experimental results showed that when the iris images down-sampled by 6% compared to the original image were restored into the high resolution ones by using the proposed method, the EER of iris recognition was reduced as much as 0.133% (1.485% - 1.352%) in comparison with that by using bi-linear interpolation

홍채 인식은 고유한 홍채 패턴을 이용하여 신원을 확인하는 생체 인식 기술이다. 일반적으로 홍채인식에서 는 홍채 직경이 200 화소(pixel) 이상 되는 고해상도 홍채 영상을 사용하며, 이런 경우 인식률 감소 없이 정확한 홍채 인식 결과를 얻는다고 알려져 있다. 이를 위해 기존의 홍채 인식 시스템들은 줌렌즈 카메라를 사용하지만, 이러한 카메라는 홍채 인식기의 가격과 크기를 증가시키는 요인이 된다. 이러한 문제를 해결하기 위하여 본 연구에서는 줌렌즈 카메라의 사용 없이 저해상도로 취득된 홍채 영상에서의 인식 정확도를 향상할 수 있는 방법을 제안한다. 본 연구에서는 기존의 방법과 비교하여 다음과 같은 두 가지 장점을 갖는다. 첫째, 기존의 연구에서는 홍채 직경이 200 화소 이하인 저해상도 영상에서의 홍채 인식 성능 감소에 대한 정량적 분석이 진행된 바 없다. 본 연구에서는 홍채 영상의 초점 정도, 눈꺼풀 및 속눈썹 가림 정도의 영향을 배제하고, 홍채 영상의 크기 변화에 따른 인식율의 저하정도를 정량적으로 파악하였다. 둘째, 한 장의 저해상도 홍채 영상을 고해상도 영상으로 복원하기 위해 홍채 영역의 에지 방향에 따라 개별적으로 다르게 학습된 다중 다층 퍼셉트론을 적용함으로써, 복원된 영상에서의 인식 정확도를 향상시켰다. 원 영상대비 6%만큼의 크기로 축소한 저해상도 홍채 영상을 고해상도 영상으로 복원한 결과, 제안하는 방법에 의한 홍채 인식의 EER이 기존의 이중선형보간법에 의한 EER보다 0.133% (1.485% - 1.352%) 만큼 감소됨을 알 수 있었다.

Keywords

Acknowledgement

Supported by : 생체인식 연구센터(BERC)

References

  1. "Information Technology. Biometric Data Interchange Formats. Iris Image Data," ISO/IEC 19794-6, 2005.
  2. "IrisAccess 4000," http://www.lgiris.com/ps/products/index.htm (accessed on 2009.7.3)
  3. "IrisPass-M," http//www.oki.com/jp/FSC/iris/en/index.html (accessed on 2009.7.3)
  4. "BM-ET 200," http://www.panasonic.com/business/security/biometrics.asp (accessed on 2009.7.3).
  5. "PIER 2.4 and HIDE Series 4," http://www.11id.com/ pages/530-mobile-id-for-military(accessed on 2009. 10. 20)
  6. "ISCAN 2," http://www.crossmatch.com/I_SCAN_2.html (accessed on 2009. 10. 20).
  7. "lris cameras," http:/ /www.jiristech.com/Products.htm (accessed on 2009. 10. 20).
  8. "Mobile eyes," http://www.retica.com!products-services-mobil-eyes.htm (accessed on 2009. 10. 20).
  9. 박강령 "홍채 인식 기술," 멀티미디어학회지, 제7권, 제2호, pp. 23-31, 2003.
  10. J. R. Matey, O. Naroditsky, K. Hanna, R. Kolczynski, D. Lolacono, S. Mangru, M. Tinker, T. Zappia, and W. Y. Zhao, "Iris on the Move: Acquisition of Images for ms Recognition in Less Constrained Environments," Proceedings of the IEEE, Vol.94, pp. 1936-1946, Nov. 2006. https://doi.org/10.1109/JPROC.2006.884091
  11. Frederick W. Wheeler, A. G. Amitha Perera, GiI Abramovich, Bing Yu, and Peter H. Tu, "Stand- off ms Recognition System," in Proc. the 2nd IEEE International Conference on Biometrics: Theory, Applications and Systems, pp. 1-7, Sept. 2008.
  12. Wenbo Dong, Zhenan Sun, Tieniu Tan, and Xianchao Qiu, "Self- adaptive Iris Image Acquisition System," in Proc. the SPIE Biometric Technology for Human Identification, Orlando, FL, Vol.6944, pp. 6-14, 2008.
  13. Soweon Yoon, Ho Gi Jung, Kang Ryoung Park, and Jaihie Kim, "Non- intrusive Iris Image Acquisition System Based on a Pan-Tilt-Zoom Camera and Light Sbipe Projection," Optical Engineering, Vol.48, No.3, pp. 137202-1-137202-15, Mar. 2009.
  14. J. Z. Huang, L. Ma,T. N. Tan, and Y. H. Wang, "Learning- Based Enhancement Model of Iris," Proc. of British Machine Vision Conference (BMVC), pp. 153-162, 2003.
  15. R. Barnard, V.P. Pauca, T.C Torgersen, R. J. Plemmons, S.Prasad, J. van der Gracht, J. Nagy, J. Chung, G. Behrmann, S. Mathews, and M. Mirotznik,"High-Resolution Image Reconstruction from Low-Resolution Imagery," Proceeding of the SPIE, Advanced Signal Processing Algorithms, Architectures, and Implementations XVI, Vol.6313, pp. D1-D13, san Diego, CA, Aug. 2006.
  16. G. Fahmy, "Super-Resolution Construction of IRIS Images from a Visual Low Resolution Face Video," National Radio Science Conference (NRSC), pp. 1-6, 2007.
  17. John G. Daugman and Cathryn Downing, "Effect of Severe Image Compression on Iris Recognition Performance," IEEE Transactions on Information Forensics and Security, Vol.3, No.1, pp. 52-61, Mar. 2008. https://doi.org/10.1109/TIFS.2007.916009
  18. S. Park, M. Park, and M. G. Kang, "Super resolution Image Reconstruction, a Technical Overview," IEEE Signal Processing Magazine, Vol.20, No.3, pp. 21-36, May 2003. https://doi.org/10.1109/MSP.2003.1203207
  19. Sang-Woong Lee, Jooyoung Parki, and Seong-Whan Lee, "Low Resolution Face Recognition Based on Support Vector Data Description," Pattern Recognition, Vol.39, No.9, 2006, pp. 1809-1812. https://doi.org/10.1016/j.patcog.2006.04.033
  20. K. Y. Shin, B. J Kang, and K. R. Park, "Super-Resolution Method Based on Multiple Multi -Layer Perceptrons for Iris Recognition," the 4th International Conference on Ubiquitous Information Technologies and Applications, pp. 322-326, Dec. 2009.
  21. S. Anna Durai and E. Anna Saro, "Images Compression with Back-Propagation Neural Network using Cumulative Distribution Function," In Proceedings of World Academy of Science, Engineering and Technology, Vol.12, Dec. 2006.
  22. "CASIA ver. 3," http//www.cbsr.ia.ac.cn/IrisDatabase.htm (accessed on 2009.7.3).
  23. 김학수 "Visual C++ 2005를 이용한 디지털 영상처리 프로그래밍 따라하기," 그린출판사, 2008.
  24. D. H. Cho, K. R. Park, D. W. Rhee, Y. G. Klln, and J. H. Yang "Pupil and Iris Localization for Iris Recognition in Mobile Phones" SNPD, Las Vegas, Nevada, USA, 2006.
  25. John G. Daugman, "High Confidence Visual Recognition of Persons by a Test of Statistical Independence," IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.15, No.11, pp. 1148-1161, Nov. 1993. https://doi.org/10.1109/34.244676
  26. John G. Daugman, "Demodulation by Complex-valued Wavelets for Stochastic Pattern Recognition," International Journal of Wavelets, Multi-resolution and Information Processing, Vol.1, No.1, pp. 1-17, 2003. https://doi.org/10.1142/S0219691303000025
  27. John G. Daugman, "The importance of being random: statistical principles of iris recognition," Pattern Recognition, Vol.36, No.2, pp. 279-291, Feb. 2003. https://doi.org/10.1016/S0031-3203(02)00030-4
  28. John G. Daugman, "How Iris Recognition Works," IEEE Trans. on Circuits and Systems for Video Tecgbikigy, Vol.14, No.1, pp. 21-29, Jan. 2004. https://doi.org/10.1109/TCSVT.2003.818350
  29. Libor Masek, "Recognition of Human Iris Patterns for Biometric Identification," Bachelors Thesis, University of Western Australia, 2003.
  30. 장영균,강병준, and 박강령, "홍채 인식을 위한 포물 허프 변환 기반 눈꺼풀 영역 검출 알고리즘," 대한전자공학회 논문지, 제44권 SP편 제01호, pp. 94-104, 2007년 1월.
  31. Y. K. Jang, B. J. Kang, and K. R. Park "A study on eyelid localization considering image focus for iris recognition," Pattern Recognition Letters, Vol.29, No.11, pp. 1698-1704, 2008. https://doi.org/10.1016/j.patrec.2008.05.001
  32. Byung Jun Kang and Kang Ryoung Park, "A Robust Eyelash Detection Based on Iris Focus Assessment," Pattern Recognition Letters, Vol.28, Issue 13, Oct. 2007, pp. 1630-1639. https://doi.org/10.1016/j.patrec.2007.04.004
  33. Kang Ryoung Park, Hyun-Ae Park, Byung Jun Kang, Eui Chul Lee, and Dae Sik jeong, "A Study on Iris Localization and Recognition on Mobile Phone." Eurasip journal on Advances in Signal Processing, Vol.2008 (2008), Nov. 2007.
  34. Hyun-Ae Park and Kang Ryoung Park, "Iris Recognition Based on Score Level Fusion by Using SVM," Pattern Recognition Letters, Vol.28, Issue 15, Nov. 2007, pp. 2019-2028. https://doi.org/10.1016/j.patrec.2007.05.017
  35. N. Macmillan, and C. Creelman, "Detection Theory: A Users Guide," New York: Cambridge University Press, 1991.
  36. A. J. Mansfield and J. L. Wayman, "2002, Best Practices in Testing and Reporting Performance of Biometric Devices," UK Govenment Biometrics Working Group.
  37. James L. Wayman. 1999, "Technical Testing and Evaluation of Biometric Identification Devices." In A Jain, R Bolle, S. Pankanti(Eds.) Biometrics: Personal Identification in Networked Society.
  38. "Lanczos resampling," http://en. wikipedia.org/wiki/Lanczos_resampling (accessed on 2009.7.3).