An Effective Face Authentication Method for Resource - Constrained Devices

제한된 자원을 갖는 장치에서 효과적인 얼굴 인증 방법

  • 이경희 (한국전자통신연구원 정보보호연구단 생체인식기술연구팀) ;
  • 변혜란 (연세대학교 컴퓨터과학과)
  • Published : 2004.09.01

Abstract

Though biometrics to authenticate a person is a good tool in terms of security and convenience, typical authentication algorithms using biometrics may not be executed on resource-constrained devices such as smart cards. Thus, to execute biometric processing on resource-constrained devices, it is desirable to develop lightweight authentication algorithm that requires only small amount of memory and computation. Also, among biological features, face is one of the most acceptable biometrics, because humans use it in their visual interactions and acquiring face images is non-intrusive. We present a new face authentication algorithm in this paper. Our achievement is two-fold. One is to present a face authentication algorithm with low memory requirement, which uses support vector machines (SVM) with the feature set extracted by genetic algorithms (GA). The other contribution is to suggest a method to reduce further, if needed, the amount of memory required in the authentication at the expense of verification rate by changing a controllable system parameter for a feature set size. Given a pre-defined amount of memory, this capability is quite effective to mount our algorithm on memory-constrained devices. The experimental results on various databases show that our face authentication algorithm with SVM whose input vectors consist of discriminating features extracted by GA has much better performance than the algorithm without feature selection process by GA has, in terms of accuracy and memory requirement. Experiment also shows that the number of the feature ttl be selected is controllable by a system parameter.

사용자를 인증하는데 생체인식(biometrics)을 사용하는 것은 보안성과 편리성에서 우수함에도 불구하고, 생체 정보를 사용하는 전형적인 인증 알고리즘은 스마트카드(smart cards)와 같은 자원이 한정된 장치에서는 실행되지 못할 수도 있다. 따라서, 제한된 자원을 갖는 장치에서 생체인식 과정이 수행되기 위해서는 적은 메모리와 처리 능력을 요구하는 가벼운 인증 알고리즘의 개발이 필요하다. 또한 생물학적 특징들 중에서 얼굴에 의한 인증은 인간에게 보다 친숙하고 얼굴 영상 획득이 비강제성을 띤다는 점에서 사용하기 가장 편리한 생체인식 기술이다. 본 논문에서는 생체인식 기술 연구의 일환으로 새로운 얼굴 인중 알고리즘을 제안한다. 이 얼굴 인증 알고리즘은 두 가지 면에서 새로운 특성을 갖는다. 그 하나는 유전자 알고리즘(GA: Genetic Algorithms) 에 의해 추출된 특징 집합(feature set)을 입력벡터로 사용하는 Support Vector Machines(SVM)을 얼굴인증에 이용함으로써 메모리 요구량을 감소시킨다는 것이다. 다른 하나는, 필요에 따라 특징 집합의 크기 조절에 대한 시스템 파라미터를 조절함으로써, 인식률은 다소 감소하더라도 인증 과정에 필요한 메모리양을 더욱 더 감소시킬 수 있다는 것이다. 이러한 특성은 메모리양이 한정된 장치에서 얼굴 인중 알고리즘을 수행할 수 있게 하는 데 상당히 효과적이다. 다양한 변화가 있는 얼굴 데이터베이스들에 대하여 실험한 결과, GA에 의해 선택된 식별력이 우수한 특징들을 SVM의 입력벡터로 사용하는 제안한 얼굴 인증 알고리즘이, GA에 의한 특징 선택 과정이 없는 알고리즘보다 정확성과 메모리 요구량에서 우수한 성능을 보임을 알 수 있다. 또한 시스템 파라미터의 변경 실험에 의해 선택될 특징의 개수가 조절될 수 있음을 보인다.

Keywords

References

  1. C. Mearns, and D. Jones, The Smart Card. SJB Research, 1999
  2. K. Lam and H. Yan, 'An Analytic-to- Holistic Approach for Face Recognition based on a Single Frontal View,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, No.7, pp. 673-686, 1998 https://doi.org/10.1109/34.689299
  3. M. A. Turk and A. P. Pentland, 'Face recognition using eigenfaces,' IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1991, pp. 586-591, Jun. 1991 https://doi.org/10.1109/CVPR.1991.139758
  4. C. Wu and J. Huang, 'Human Face Profile Recognition by Computer,' Pattern Recognition, Vol. 23, No. 3/4, pp. 255-259, 1990 https://doi.org/10.1016/0031-3203(90)90013-B
  5. R. Brunelli and T. Poggio, 'Face Recognition: Features versus Templates,' IEEE Trans. PAMI. , Vol. 15, pp.1042-1052, 1993 https://doi.org/10.1109/34.254061
  6. V. Vapnik, Statistical Learning Theory, John Wiley & Sons, New York, 1998
  7. Vladimir N. Vapnik, The Nature of Statistical Learning Theory, Springer-Verlag New York, 2000
  8. E. Osuna, R. Feund, and F. Girosi, 'Training Support Vector Machines: an Application to Face Detection,' Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp.130-136, 1997 https://doi.org/10.1109/CVPR.1997.609310
  9. J. Huang, X. Shao, and H. Wechsler, 'Face Pose Discrimination using Support Vector Machines,' Proceedings of International Conference on Pattern Recogniton, pp. 154-156, 1998 https://doi.org/10.1109/ICPR.1998.711102
  10. G. Guo, S. Z. Li, and K. L. Chan, 'Support vector machines for face recognition:' Image and Vision Computing 19, pp. 631-638, 200l https://doi.org/10.1016/S0262-8856(01)00046-4
  11. K. Jonsson, J. Matas, J. Kittler, and Y. Li, 'Learning Support Vectors for Face Verification and Recognition,' Proceedings of International Conference on Automatic Face and Gesture Recognition, pp. 208-213, 2000 https://doi.org/10.1109/AFGR.2000.840636
  12. Y. Li, S. Gong, and H. Liddell, 'Support Vector Regression and Classification based Multi-View Face Detection and Recognition,' Proceedings of International Conference on Automatic Face and Gesture Recognition, pp. 300-305, 2000 https://doi.org/10.1109/AFGR.2000.840650
  13. P. Jonathon Phillips, 'Support Vector Machines Applied to Face Recognition,' Advances in Neural Information Processing Systems 11, MIT Press, pp. 803-809, 1999
  14. David E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, 1989
  15. Kyunghee Lee, Yongwha Chung, and Hyeran Byun, 'SVM-based face verification with feature set of small size,' IEE Electronics Letters, Vol.38, No.15, pp.787-789. 2002 https://doi.org/10.1049/el:20020591
  16. Yale Face Database, http://cvc.yale.edu/projects/yalefaces/yalefaces.html
  17. ORL Face Database, http://www.cam-orl.co.uk/facedatabase.html
  18. Postech Face Database, http://nova.postech.ac.kr
  19. Jihoon Yang and Vasant Honavar, 'Feature Subset Selection using A Genetic Algorithm,' Feature Extraction, Construction and Selection: A Data Mining Perspective, Kluwer Academic Publishers, pp. 117-136, 2001
  20. H. Vafaie and K. DeJong, 'Feature Space Transformation Using Genetic Algorithms,' IEEE Intelligent Systems, March/April, pp. 57-65, 1998 https://doi.org/10.1109/5254.671093
  21. Rafael C. Gonzalez, and Richard E. Woods, Digital Image Processing, Addison Wesley Longman, 1992
  22. C. Sanderson. Information Fusion and Person Verification Using Speech and Face Information, IDIAP Research Report 02-33, 2002