Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

A Study on Face Recognition using DCT/LDA

DCT/LDA 기반 얼굴 인식에 관한 연구

  • 김형준 (한양대학교 전자통신컴퓨터공학부) ;
  • 정병희 (KBS 방송기술연구팀) ;
  • 김회율 (한양대학교 전자통신컴퓨터공학부)
  • Published : 2005.11.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a method to recognize a face using DCT/LDA where LDA is applied to DCT coefficients of an input face image. In the proposed method, SSS problem of LDA due to less number of training data than the size of feature space can be avoided by expressing an input image in low dimensional space using DCT coefficients. In terms of the recognition rate, both the proposed method and the PCA/LDA method have shown almost equal performance while the training time of the proposed method is much shorter than the other. This is because DCT has the fixed number of basis vectors while the property of energy compaction rate is similar to that of PCA. Although depending on the number of coefficients employed for the recognition, the experimental results show that the performance of the proposed method in terms of recognition rate is very comparable to PCA/LDA method and other DCT/LDA methods, and it can be trained 13,000 times faster than PCA/LDA method.

본 논문에서는 입력된 얼굴 영상으로부터 구한 DCT 계수에 대해 LDA를 적용하는 DCT/LDA를 이용한 얼굴 인식 방법을 제안한다. 제안된 방법은 적은 수의 DCT 계수를 이용하여 입력 영상을 저차원으로 표현함으로써 특징 공간의 차수보다 트레이닝 데이터의 수가 적은 경우 발생하는 LDA의 SSS 문제를 해결한다. DCT는 기저 벡터가 일정하며 PCA와 유사한 에너지 압축 효율을 가지기 때문에 제안된 방법은 기존의 PCA/LDA 방법보다 학습 속도는 빠르면서 실제 얼굴인식 시스템에 적용이 가능한 정도의 얼굴 인식율을 기대할 수 있다. 실험을 통해 제안된 방법이 PCA/LDA 방법과 유사한 얼굴 인식 성능을 보이면서 약 13,000배 빠르게 학습되는 것을 확인하였고, 기존의 Block-DCT/LDA 방법과 유사하거나 향상된 인식 결과를 확인하였다.

Keywords

References

  1. R. Gross, I. Matthews, and S. Baker, 'Appearance-Based Face Recognition and Light-Fields,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 4, pp. 449-465, April 2004 https://doi.org/10.1109/TPAMI.2004.1265861
  2. Juwei Lu, K.N. Plataniotis, and A.N. Venetsanopoulos, 'Face recognition using LDA based algorithms', IEEE Transactions on Neural Networks, vol.14, no.1, pp.195-200, January 2003 https://doi.org/10.1109/TNN.2002.806647
  3. A.Martinez and A.Kak: 'PCA versus LDA', IEEE Trans. On PAMI, 23(2):228-233, 2001 https://doi.org/10.1109/34.908974
  4. W. Zhao, R. Chellappa, and A. Krishnaswamy, 'Discriminant Analysis of Principal Components for Face Recognition,' Third IEEE International Conference on Automatic Face and Gesture Recognition, pp. 336-341, April 1998 https://doi.org/10.1109/AFGR.1998.670971
  5. 장혜경, 오선문, 강대성, 'PCA 기반 LDA 혼합 알고리즘을 이용한 실시간 얼굴인식 시스템 구현,' 전자공학회논문지, 제41권 SP편, 제4호, 45-50쪽, 2004년 7월
  6. H.-J. Lee, H.-J. Kim, and W.-Y. Kim, 'Face Recognition using Component-based DCT/LDA,' 제2회 BERC 생체인식 워크샵, pp. 219-222, 2004년 2월
  7. H.-J. Lee, H.-J. Kim, and W.-Y. Kim, 'Face Recognition Using Component-based DCT/LDA,' International Workshop on Advanced Image Technology (IWAIT2005), pp. 25-30, January 2005
  8. S. Annadurai and A. Saradha, 'Discrete Cosine Transform Based Face Recognition Using Linear Discriminant Analysis,' IJSIT Lecture Note of International Conference on Intelligent Knowledge Systems, Vol. 1, No. 1, pp. 90-94, August 2004
  9. X.-Y. Jing and D. Zhang, 'A Face and Palmprint Recognition Approach Based on Discriminant DCT Feature Extraction,' IEEE Transactions on Systems, Man, and Cybernetics, Vol. 34, No. 6, pp. 2405-2415, December 2004 https://doi.org/10.1109/TSMCB.2004.837586
  10. M. J. Er, W. Chen, and S. Wu, 'High-Speed Face Recognition Based on Discrete Cosine Transform and RBF Neural Networks,' IEEE Transactions on Neural Networks, Vol. 16, No. 3, pp. 679-691, May 2005 https://doi.org/10.1109/TNN.2005.844909
  11. A. Pnevmatikakis and L. Polymenakos, 'Comparison of Eigenface-Based Feature Vectors under Different Impairments,' 17th International Conference on Pattern Recognition (ICPR'04), Vol. 1, pp. 296-299, August 2004 https://doi.org/10.1109/ICPR.2004.1334111
  12. C. Sanderson, 'Automatic Person Verification Using Speech and Face Information,' , Griffith University, February 2003
  13. Z. M. Hated and M. D. Levine, 'Face Recognition Using the Discrete Cosine Transform,' International Journal of Computer Vision, Vol. 43, No. 3, pp. 167-188, 2001 https://doi.org/10.1023/A:1011183429707
  14. Z. Jianke, V. M. I, and M. P. Un, 'Face Recognition Using 2D DCT with PCA,' Chinese Conference on Biometric Recognition (Sinobiometrics'03), December 2003
  15. V. V. Kohir and U. B. Desai, 'Face Recognition Using a DCT-HMM approach,' IEEE Workshop on Applications of Computer Vision (WACV'98), pp. 226-231, 1998 https://doi.org/10.1109/ACV.1998.732884
  16. R. C. Gonzalez and R. E. Woods, Digital Image Processing, second ed., Prentice Hall, 2002
  17. J. Kittler, Y. P. Li, and J. Matas, 'On Matching Scores for LDA-based Face Verification,' The British Machine Vision Conference (BMVC2000), pp. 42-51, September 2000
  18. http://www.intel.com/research/mrl/research/opencv/
  19. A.M. Martinez and R. Benavente, 'The AR Face Database,' CVC Technical Report 24, June 1998
  20. http://www.uk.research.att.com/facedatabase.html
  21. K. Fukunaga, Introduction to Statistical Pattern Recognition, second ed., Academic Press, 1990
  22. M. Turk and A. Pentland, 'Eigenfaces for recognition,' International Journal of Cognitive Neuroscience, Vol. 3, No. 1, pp. 71-86, 1991 https://doi.org/10.1162/jocn.1991.3.1.71
  23. L. Sirivich and R. Everson, 'Management and analysis of large scientific datasets,' International Journal of Supercomputer Applications, Vol. 16, No. 1, pp. 50-68, 1992