A Method of Generating Changeable Face Template for Statistical Appearance-Based Face Recognition

통계적 형상 기반의 얼굴인식을 위한 가변얼굴템플릿 생성방법

  • Lee, Chul-Han (Biometric Engineering Research Center, Yonsei University) ;
  • Jung, Min-Yi (Biometric Engineering Research Center, Yonsei University) ;
  • Kim, Jong-Sun (Biometric Engineering Research Center, Yonsei University) ;
  • Choi, Jeung-Yoon (Biometric Engineering Research Center, Yonsei University) ;
  • Kim, Jai-Hie (Biometric Engineering Research Center, Yonsei University)
  • 이철한 (연세대학교 생체인식 연구센터) ;
  • 정민이 (연세대학교 생체인식 연구센터) ;
  • 김종선 (연세대학교 생체인식 연구센터) ;
  • 최정윤 (연세대학교 생체인식 연구센터) ;
  • 김재희 (연세대학교 생체인식 연구센터)
  • Published : 2007.03.25

Abstract

Changeable biometrics identify a person using transformed biometric data instead of original biometric data in order to enhance privacy and security in biometrics when biometric data is compromised. In this paper, a novel scheme which generates changeable face templates for statistical appearance-based face recognition is proposed. Two different original face feature vectors are extracted from two different appearance-based approaches, respectively, each original feature vector is normalized, and its elements are re-ordered. Finally a changeable face template is generated by weighted addition between two normalized and scrambled feature vectors. Since the two feature vectors are combined into one by a two to one mapping, the original two feature vectors are not easily recovered from the changeable face template even if the combining rule is known. Also, when we need to make new changeable face template for a person, we change the re-ordering rule for the person and make a new feature vector for the person. Therefore, the security and privacy in biometric system can be enhanced by using the proposed changeable face templates. In our experiments, we analyze the proposed method with respect to performance and security using an AR-face database.

가변생체인식(Changeable Biometrics)이란 생체정보의 도난이나 도용 시 개인의 프라이버시를 보호하기 위해 원 생체정보를 사용하지 않고, 생체정보를 변환하여 변환된 생체정보로 개인을 인증하는 방법이다. 본 논문은 통계적 형상 기반의 얼굴인식(Statistical appearance based face recognition)에 적용될 수 있는 가변얼굴템플릿 생성 방법에 대해 제안한다. 상이한 두 개의 통계적 형상 기반의 얼굴특징 방법을 이용하여 두 개의 얼굴특징벡터를 추출하고, 추출된 두 개의 얼굴특징벡터를 정규화 후 각 특징벡터들의 요소의 순서를 재배열 시킨다. 가변얼굴템플릿은 정규화 되고 순서가 재배열된 특징벡터들의 가중 합으로 생성된다. 두 개의 서로 다른 얼굴특징벡터의 가중 합으로 하나의 가변얼굴템플릿을 생성하므로, 가중 합의 방법과 생성된 가변얼굴템플릿을 알더라도 원 얼굴 특징벡터를 복원할 수 없다. 또한, 생성된 가변얼굴템플릿의 도난 시 새로운 가변얼굴템플릿의 생성은 각 벡터의 순서를 재배열시키는 규칙을 변경함으로써 가능하다. 그러므로 제안한 가변얼굴템플릿을 이용하여 개인 인증 시, 개인의 얼굴템플릿을 도난당하더라도 원 얼굴특징정보를 복원 할 수 없고 또한 새로운 가변얼굴템플릿으로 대체 할 수 있어 생체정보의 도난 시 발생할 수 있는 프라이버시 침해의 문제를 해결 할 수 있다. 제안한 방법은 AR-face DB를 이용하여 성능과 보안성에 대해 평가하였다.

Keywords

References

  1. N. K. Ratha, J. H. Connell, and R. M. Bolle, 'Enhancing security and privacy in biometrics-based authentication systems,' IBM Systems Journal, vol. 40, no. 3, 2001
  2. R. M. Bolle, J.H. Connel, and N.K. Ratha, 'Biometrics Perils and Patches,' Pattern Recognition, vol. 35, pp. 2727-2738, 2002 https://doi.org/10.1016/S0031-3203(01)00247-3
  3. M. Savvides, B. V. K. Vijaya Kumar, and P. K. Khosla, 'Cancelable Biometric Filters for Face Recognition,' Proceedings of the 17th International Conference on Pattern Recognition, 3, pp. 922-925, Cambridge, UK, 2004
  4. A.B.J. Teoh, D.C.L. Ngo, and A. Goh, 'BioHashing: two factor authentication featuring fingerprint data and tokenised random number,' Pattern Recognition, vol. 37, pp. 22452255, November, 2004 https://doi.org/10.1016/j.patcog.2004.04.011
  5. A.B.J. Teoh, D.C.L. Ngo, and A. Goh, 'Personalised cryptographic key generation based on FaceHashing,' Computers and Security, vol. 23, no. 7, pp. 606-614, 2004 https://doi.org/10.1016/j.cose.2004.06.002
  6. A.B.J. Teoh, and D.C.L. Ngo, 'Cancellable biometrics featuring with tokenized random number,' Pattern Recognition Letter, vol. 26, no. 10, pp. 14541460, 2005 https://doi.org/10.1016/j.patrec.2004.11.021
  7. T. Connie, A. Teoh, M. Goh, and D. Ngo, 'PalmHashing: a novel approach for dual-factor authentication,' Pattern Analysis and Applications, vol. 7, no. 3, pp. 255 268, 2004 https://doi.org/10.1007/s10044-004-0223-4
  8. Y.H. Pang, A.B. J Teoh, and D.C.L. Ngo, 'Palmprint based cancelable biometric authentication system,' International Journal of Signal Processing, vol. 1, no. 2, pp. 98-104, 2004
  9. C. S. Chin, A.B.J. Teoh, and D.C.L. Ngo, 'High security Iris verificationsystem based on random secret integration,' Computer Vision and Image Understanding, vol. 102, Iss. 2, pp. 169-177, 2006 https://doi.org/10.1016/j.cviu.2006.01.002
  10. A. Kong, K. H. Cheung, D. Zhang, M. Kamel and J. You, 'An analysis of BioHashing and its variants,' Pattern Recognition, In Press, Corrected Proof, Available online, 27 December 2005
  11. J. N. Kang, D. H. Nyang and K. H. Lee, 'Two Factor Face Authentication Scheme with Cancelable Feature,' Lecture notes in Computer Science 3781, pp.67-76, Oct. 2005
  12. R. Ang. R.Safavi-Naini, and L.McAven, 'Cancelable Key-Based Fingerprint Templates,' Information Security and Privacy: 10th Australasian Conference, ACISP, pp. 242-252, Brisbane, Australia, 2005
  13. M. Y. Jung, C. H. Lee, J. S. Kim, J. Y. Chol, and J. H. Kim, 'A Changeable Biometric System for Appearance-Based Face Recognition,' Biometric Consortium Conference (BCC 2006), Baltimore, USA, 2006
  14. M.A. Turk and A.P. Pentland, 'Eigenfaces for Recognition,' Cognitive Neuroscience, vol. 3, no. 1, pp. 71-86, 1991 https://doi.org/10.1162/jocn.1991.3.1.71
  15. M. S. Bartlett, J. R. Movellan, and T. J. Sejnowski, 'Face Recognition by Independent Component Analysis,' IEEE Trans. Neural Networks, vol. 13, no. 6, pp. 1450-1464, 2002 https://doi.org/10.1109/TNN.2002.804287
  16. A. Hyvarinen and E. Oja, 'Independent component analysis: a tutorial,' http://www.cis.hut.fi/~aapo/papers/IJCNN99_tutori alweb/, 1999
  17. D. D. Lee and H. S. Seung, 'Learning the parts of objects by non-negative matrix factorization,' Nature, vol. 401, pp. 788-791, 1999 https://doi.org/10.1038/44565
  18. A.M. Martinez and R. Benavente, 'The AR Face Database,' CVC Tech, 1998
  19. D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar, Handbook of Fingerprint Recognition, Springer, New York, 2003v