The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지

A Study on Face Recognition Based on Modified Otsu's Binarization and Hu Moment

변형 Otsu 이진화와 Hu 모멘트에 기반한 얼굴 인식에 관한 연구

  • 이형지 (인하대학교 전자공학과 디지털신호처리연구실) ;
  • 정재호 (인하대학교 전자공학과 디지털신호처리연구실)
  • Published : 2003.11.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a face recognition method based on modified Otsu's binarization and Hu moment. Proposed method is robust to brightness, contrast, scale, rotation, and translation changes. As the proposed modified Otsu's binarization computes other thresholds from conventional Otsu's binarization, namely we create two binary images, we can extract higher dimensional feature vector. Here the feature vector has properties of robustness to brightness and contrast changes because the proposed method is based on Otsu's binarization. And our face recognition system is robust to scale, rotation, and translation changes because of using Hu moment. In the perspective of brightness, contrast, scale, rotation, and translation changes, experimental results with Olivetti Research Laboratory (ORL) database and the AR database showed that average recognition rates of conventional well-known principal component analysis (PCA) are 93.2% and 81.4%, respectively. Meanwhile, the proposed method for the same databases has superior performance of the average recognition rates of 93.2% and 81.4%, respectively.

본 논문에서는 변형 Otsu 이진화 방법과 Hu 모멘트를 기반으로 밝기, 명암도, 크기, 회전, 위치 변화에 강인한 얼굴 인식 방법을 제안한다. 제안하는 변형 Otsu 이진화 방법은 기존의 Otsu 이진화 방법으로부터 또 다른 문턱치 값을 결정하고 이로부터 얻어진 이진 얼굴 영상 2개를 사용함으로써 이진 영상 하나보다 고차원의 특징벡터를 추출할 수 있고, 기존의 Otsu 이진화 방법과 마찬가지로 밝기 및 명암도 변화에 강인한 속성을 가지고 있다. 특징 값으로는 Hu 모멘트를 사용함으로써 크기, 회전, 위치 변화에 강인한 특성을 추가로 가지고 있다 기존의 주요 성분 분석(Principal Component Analysis, PCA) 방법과 제안한 방법을 비교 실험한 결과, 위에서 언급한 5가지 다양한 환경 변화에 대하여 PCA 방법의 평균 인식률은 olivetti Research Laboratory (ORL) 데이터베이스와 AR 데이터베이스에 대해서 각각 68.4%와 51.2%이고, 제안한 방법의 평균 인식률은 각각 93.2%와 81.4%로서 제안한 방법의 인식 성능이 우수함을 확인하였다.

Keywords

References

  1. R Chellappa and S. Sirohey, 'Human and Machine Recognition of Faces: A Survey,'Proceedings of the IEEE. vol. 83, no. 5. May1995
  2. S. Pankanti, R M. Bolle, and A. Jain,'Biometrics: The Future of Identification', Computer Magazine, pp. 46-49, Feb. 2000
  3. A. P. Pentland and M. A. Turk, 'Face recognition using eigenfaces,' in Proc. the International Conference on Pattem Recognition, pp.586-591, 1994
  4. P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, 'Eigenfaces vs. Fisherfaces: recognition using class spedSc linear projection,' IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp711-720, July 1997 https://doi.org/10.1109/34.598228
  5. Chengjun Liu and Harry Wechsler, 'Gabor Feature Based Classification Using the Enhanced Fisher Linear Discriminant Model for Face Recognition,' IEEE Trans. on Image Processing, vol. 11, no. 4, April 2002
  6. Juwei Lu, Kostantinos N. Plataniotis, and Anastasios N. Venetsanopoulos, 'Face Recognition Using LDA-Based Algonthms,'IEEE. Trans. on Neural Networks, vol. 14, no.1, Jan. 2003
  7. Juwei Lu, Kostantinos N. Plataniotis, and Anastasios N. Venetsanopoulos, 'Face Recognition Using Kernel Direct Discriminant Analysis Algohthms,' IEEE. Trans. on Neural Networks, vol. 14, no. 1, Jan. 2003
  8. Marian Stewart Bartlett, R Movellan, andTerrence J. Sejnowski, 'Face Recognition by Independent Component Analysis,' IEEE Trans. on Neural Networks, vol. 13, no. 6, Nov. 2002
  9. B. Duc, S. Fisher, and J. Bigun, 'Face authentication with Gabor information on deformable graphs,' IEEE Trans. on Image Processing, vol. 8, no. 4, April 1999
  10. S. C. Lee, H. S. Kim, S. J. Park, and S. H Park, 'Face recognition technology in the dynamic link architecture,' in Proc the International Conference on Etectrical Engineering, pp. 265-268, 1999
  11. L. Wiskott, J. M. Fellous, N. Kruger, and C.Malsburg, 'Face Recognition by Elastic Bunch Graph Matching,' IEEE Trans. Pattern AnaIysis and Machine Intelligence, vol. 19,no. 7, pp. 775-779, 1997 https://doi.org/10.1109/34.598235
  12. Chengjun Liu, and Harry Wechsler,'Independent Component Analysis of Gabor Features for Face Recognition,' IEEE. Trans.on Neural Networks, vol. 14, no. 4, 2003. 7
  13. 이형지, 정재호, "Fisherface 알고리즘과 Fixed Graph Matching을 이용한 얼굴 인식,' 전자공학회논문지, 제 38권 SP편, 제6호, 2001
  14. H. J. Lee, W. S. Lee, and J. H Chung, 'Face recognition using fisherface algorithm And Elastic graph matching,' in Proc. the International Conference on Image Processing, pp. 998-1001, 2001
  15. Chengjun Liu and Harry Wechsler, 'Gabor Feature Based Classification Using the Enhanced Fisher Linear Discriminant Model for Face Recognition,' IEEE. Trans. on Image Processing, vol. 11, no. 4, April 2002
  16. 심영미, 장주석, 김종규, 'Fourier 변환된 얼굴의 진폭스펙트럼의 Karhunen-Loeve 근사 방법에 기초한 변위불변적 얼굴인식,' 전자공학회논문지, 제35권, C편, 제3호, 1998
  17. M Nixon, 'Automated facial recognition and its potential for security,' in IEE Colloq. Dig.(80): Colloq. on MMI in Computer Security,pp. 5/1-4, 1986
  18. J. Zhang, Y. Yan, and M. Lades,'Face Recognition: Eigenface, Elastic Matching, and Neural Nets,' in Proc of the IEEE, vol. 85,no. 9, pp. 1422-1435, September 1997 https://doi.org/10.1109/JPROC.1997.628711
  19. M. S. Oh, D. W. Kim, and D. S. Jeong, 'Face Identification System Using Combined FacialFeatures and Counter-Propagation NeuralNetwork,'신호처리합동학술대회, 제6권, pp.266-269, 1993
  20. Y. Cao and K. H. Leung, 'Face RecognitionUsing Line Edge MaP,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24,no. 6, pp. 764-779, 2002 https://doi.org/10.1109/TPAMI.2002.1008383
  21. Olivier de Vel and Stefan Aeberhard,'Line-Based Face Recognition under Varing Pose,' IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 21, no. 10, Oct.1999
  22. lan Craw, Nicholas Costen, Takashi Kato, and Shigeru Akamatsu, 'How Should We Represent Faces for Automatic Recognition,'IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 21, no. 8, 1999. 8
  23. A. M. Martinez and R. Benavente, 'The AR Face Database,' CVC Technical Report no.24, June 1998
  24. 김광섭, 이상묵, 정동석, '윤곽선 방향의 히스토그램과 Sampled Spot Matching을 이용한 이치형상의 인식 알고리즘,' 전자공학회논문지, vol. 28, no. 10, pp. 69-77, 1992
  25. N. Otsu, 'A threshold selection method fromgray level histogram,' IEEE SMC-9, no. 1,pp. 62-66, 1979
  26. K. Fukunaga- Introduction to StatisticalPattern Recogntion, New York Academic,1972
  27. R C. Gonzalez, P. Wintz, DigitaI image processing, Addision-Wesley, 1987
  28. Hyung Ji Lee and Jae Ho Chun, 'Brightness,Contrast, Scaling, Rotation and Translation Invariant Feature Extraction by Multi-level Thresholding and Moment,' submitted toIEICE, 2003
  29. M. K. Hu, 'PattErn recognition by moment invariants,' Proc. IEEE, vol. 49, no. 9, p.1428, Sept. 1961
  30. M K. Hu, 'Visual pattern recognition by moment invariants,' IRE Transactions on Information Theory, vol. 17-8, no. 2, pp.179-187, Feb. 1962