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

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

로그폴라 사상과 어파인 변환을 이용한 새로운 템플릿 기반 얼굴 인식

New Template Based Face Recognition Using Log-polar Mapping and Affine Transformation

  • 김문갑 (용인송담대학 디지털전자정보과) ;
  • 최일 (구미1대학 정보통신과) ;
  • 진성일 (경북대학교 전자전기컴퓨터학부)
  • Kim, Mun-Gab (Yong-In Songdam College, Dept. of Digital Electronics & Information) ;
  • Choi, Il (Kumi College, Dept. of Information and Communications) ;
  • Chien, Sung-Il (Kyungpook National University, School of Electrical Engineering and Computer Science)
  • 발행 : 2002.03.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

이 논문에서는 크기와 영상 평면상에서 회전 (in-plane rotation) 변화를 가지는 정면 얼굴 영상의 인식성능을 향상시키기 위하여, 새로운 템플릿 (template) 기반 접근 방법들을 제안한다. 인식 성능을 향상시키기 위한 템플릿들은 크기와 회전 변화가 다른 다수의 영상들을 선형 또는 비선형 연산에 의하여 생성된다. 얼굴의 크기와 영상 평면에서 회전 변화에 무관한 얼굴의 특징을 추출하기 위하여 어파인 (affine) 변환, 로그폴라 (log-polar) 사상, 그리고 로그폴라 영상에 기반한 FFT들이 이용된다. 제안된 방법들은 인식률과 수행 시간 측면에서 비교된다. 실험 결과로부터 제안된 템플릿을 이용한 방법들의 인식률이 한 장의 영상으로 생성된 템플릿을 이용한 방법들의 인식률보다 우수함을 나타낸다. 어파인 변환을 이용한 방법의 인식률이 로그폴라 사상을 이용한 방법과 로그폴라 영상에 기반한 FFT 방법의 인식률보다 우수하며, 수행 시간 측면에서는 로그폴라 사상을 이용한 방법이 가장 빠르다.

This paper presents the new template based human face recognition methods to improve the recognition performance against scale and in-plane rotation variations of face images. To enhance the recognition performance, the templates are generated by linear or nonlinear operation on multiple images including different scales and rotations of faces. As the invariant features to allow for scale and rotation variations of face images, we adopt the affine transformation, the log-polar mapping, and the log-polar image based FFT. The proposed recognition methods are evaluated in terms of the recognition rate and the processing time. Experimental results show that the proposed template based methods lead to higher recognition rate than the single image based one. The affine transformation based face recognition method shows marginally higher recognition rate than those of the log-polar mapping based method and the log-polar image based FFT, while, in the aspect of processing time, the log-polar mapping based method is the fastest one.

키워드

참고문헌

  1. S. Pankanti, R.M. Bolle, and A. Jain, Biometrics : Personal identification in networked soceity, Kluwer Academic, Norwell, Mass., 1999
  2. P.J. Philips, A. Martin, C.L. Wilson, and M. Przybocki, 'An introduction to evaluating biometric systems,' IEEE Computer : Innovative Technology for Computer Personals, pp. 56-64, Feb. 2000 https://doi.org/10.1109/2.820040
  3. R. Brunelli and T. Poggio, 'Face recognition: Features versus templates,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol, 15, no. 10, pp. 1042-1052, 1993 https://doi.org/10.1109/34.254061
  4. B. Moghaddam and A. Pentland, 'Probabilistic visual learning for object representation,' IEEE Trans. Pattern Analysis and Machine Intelli-gence, vol. 19, no.7, pp. 696-710, 1997 https://doi.org/10.1109/34.598227
  5. X. Jia and M.S. Nixon, 'Extending the feature vector for automatic face recognition,' IEEE Trans. Pattern Analysis and Machine Intelli-gence, vol. 17, no. 12, pp. 1162 - 1176, 1995 https://doi.org/10.1109/34.476509
  6. J. Zhang, Y. Yan, and M Lades, 'Face recognition : Eigenface, elastic matching, and neural nets,' Proc, of The IEEE, vol. 85, no. 9, pp. 1423-1435, 1997 https://doi.org/10.1109/5.628712
  7. G. Wolberg, Digital Image Warping, pp. 42-45, IEEE Computer Society Press, Los Alamitos, CA, 1990
  8. L. Wiskott, J.-M Fellous, N. Kruger, and C. von der Malsburg, 'Face recognition by elastic bunch graph matching,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 775-779, 1997 https://doi.org/10.1109/34.598235
  9. Y. Adini, Y. Moses, and S. Ullman, 'Face recognition: The problem of compensating for changes in illumination direction,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 721-732, 1997 https://doi.org/10.1109/34.598229
  10. M. Bolduc and M.D. Levine, 'A review of biologically motivated space-variant data reduc-tion models for robotic vision,' Computer Vision and Image Understanding, vol. 69, no. 2, pp. 170-184, 1998 https://doi.org/10.1006/cviu.1997.0560
  11. S.-I. Chien and I. Choi, 'Face and facial landmarks location based on log-polar map-ping,' S.-W. Lee, H.H. Buelthoff, and T. Poggio Eds., BMCV 2000, Lecture Notes in Computer Science 1811, pp. 379-386, 2000 https://doi.org/10.1007/3-540-45482-9_38
  12. 최 일, '로그폴라 영상 변환을 이용한 얼굴 검출 및 인식', 경북대학교 박사학위 논문, 2000년 12월
  13. K. -M. Lam, H. Yan, 'Location and Extracting the Eye in Human Images,' Pattern Recogni-tion, vol. 29, no. 5, pp. 771-779, 1996 https://doi.org/10.1016/0031-3203(95)00119-0
  14. J. Y. Deng, F. Lai, 'Region-Based Template Deformation and Masking for Eye-Feature Extraction and Description,' Pattern Recogni-tion, vol. 30, no. 5, pp. 403-419, 1997 https://doi.org/10.1016/S0031-3203(96)00086-6