방사 기저 함수 신경망을 이용한 3차원 얼굴인식

3D face recognition based on radial basis function network

  • 양욱일 (연세대학교 전기전자공학과) ;
  • 손광훈 (연세대학교 전기전자공학과)
  • Yang, Uk-Il (Yonsei University, Dept. of Electrical & Electronic Engineering, Biometric Engineering Research Center) ;
  • Sohn, Kwang-Hoon (Yonsei University, Dept. of Electrical & Electronic Engineering, Biometric Engineering Research Center)
  • 발행 : 2007.03.25

초록

본 논문에서는 3차원 얼굴인식을 위한 방사 기저 함수 신경망 기반의 새로운 전역적 형태 특징과 그 특징을 추출하는 방법을 제안한다. 방사 기저 함수 신경망은 방사 기저 함수들의 가중합으로써, 얼굴 형태 정보의 비선형성을 방사 기저 함수의 선형합으로 잘 표현한다. 이 논문에서는 얼굴의 가로 방향 프로파일을 학습된 방사 기저 함수 신경망에 적용시켰을 때 생성되는 가증치를 새로운 전역적 형태 특징으로 제안한다. 제안하는 전역적 형태 특징의 경우 국소적 특징의 특성을 가지며, 일반적인 전역적 특징의 특성인 특징의 복잡도도 감소시킨다. 100명의 데이터베이스 영상과 100명에 대한 서로 다른 3개의 포즈를 포함하는 300개의 테스트 영상을 이용한 실험에서 제안하는 전역적 형태 특징과 은닉 마르코프 모델을 이용한 특징 비교를 통해서 94.7%의 인식률을 얻었다.

This paper describes a novel global shape (GS) feature based on radial basis function network (RBFN) and the extraction method of the proposed feature for 3D face recognition. RBFN is the weighted sum of RBfs, it well present the non-linearity of a facial shape using the linear combination of RBFs. It is the proposed facial feature that the weights of RBFN learned by the horizontal profiles of a face. RBFN based feature expresses the locality of the facial shape even if it is GS feature, and it reduces the feature complexity like existing global methods. And it also get the smoothing effect of the facial shape. Through the experiments, we get 94.7% using the proposed feature and hidden markov model (HMM) to match the features for 100 gallery set with those for 300 test set.

키워드

참고문헌

  1. R. Chellappa, C. L. Wilson, and S. Sirohey, 'Human and machine recognition of faces: A survey,' Proceedings of the IEEE, vol. 83, no. 5, pp. 705-740, May 1995 https://doi.org/10.1109/5.381842
  2. W. Zhao, R. Chellappa, A. Rosenfeld, and P.J. Phllips, 'Face recognition: A survey,' CVL Technical Report, Center for Automation Research, University of Maryland at College Park, Oct. 2000
  3. Stan Z. Li, Anil K. Jain, 'Handbook of face recognition', Springer Science+Bussience Media, Inc. 2004
  4. H. Song, S. Lee, J. Kim and K.Sohn, '3D sensor based face recognition,' Applied Optics, Vol. 44, No. 5, pp. 677-687, Feb. 2005 https://doi.org/10.1364/AO.44.000677
  5. J. Y. Cartoux, J. T. LaPreste, and M. Richetin, 'Face authentication or recognition by proifle extraction from range images,' in Proc. of the Workshop on Interpretation of 3D Scenes, pp. 194-199, 1989
  6. J. C. Lee and E. Milios. 'Matching range images of human faces,' in International Conference on Computer Vision, pp. 722-726, 1990
  7. G. Gordon, 'Face recognition based on depth and curvature features,' in Computer Vision and Pattern Recognition, pp. 108-110, 1992
  8. T. Nagamine, T. Uemura, and I. Masuda, '3D facial image analysis for human identification,' in International Conference on Pattern Recognition, pp.324-327, 1992
  9. C. Chua, R. Jarvis, 'Point Signatures: A New Representation for 3D Object Recognition,' International Journal of Computer Vision vol. 25, No. 1, pp. 63-85, 1997 https://doi.org/10.1023/A:1007981719186
  10. B. Achermann, X. Jiang, and H. Bunke, 'Face recognition using range images,' in International Conference on Virtual Systems and MultiMedia, pp. 129-136, 1997
  11. C. Hesher, A. Srivastava, and G. Erlebacher, 'A novel technique for face recognition using range images,' in Seventh Int'l Symposium on Signal Processing and Its Applications, 2003
  12. P. J. Besl and N. D. McKay. 'A method for registration of 3-d shapes,' IEEE Trans. Pat. Anal. and Mach. Intel. vol. 14, No, 2, pp 239-256, Feb 1992 https://doi.org/10.1109/34.121791
  13. G. Medioni and R. Waupotitsch, 'Face recognition and modeling in 3D,' in IEEE International Workshop on Analysis and Modeling of Faces and Gestures, pp. 232-233, 2003
  14. Intel$circedR$ Open Source Computer Vision Library, http://www.intel.com/software/products/ipp/index. htm
  15. J.O. Rawlings, 'Applied Regression Analysis,' Wadsworth & Brooks/Cole, Pacific Grove, CA, 1988