한국정보과학회논문지:소프트웨어및응용 (Journal of KIISE:Software and Applications)

한국정보과학회 (Korean Institute of Information Scientists and Engineers)
권호 표지

조명얼굴 영상을 위한 협력적 지역 능동표현 모델

Collaborative Local Active Appearance Models for Illuminated Face Images

  • 양준영 (연세대학교 컴퓨터과학과) ;
  • 고재필 (금오공과대학교 컴퓨터공학부) ;
  • 변혜란 (연세대학교 컴퓨터과학과)
  • 발행 : 2009.10.15
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

얼굴영상 공간에서 얼굴영상들은 조명이나 포즈에 의해 비선형적 분포를 갖는다. 이들을 선형모델에 기반을 둔 AAM으로 모델링 하는 것은 한계가 있다. 본 논문에서는 얼굴영상에 대한 몇 개의 군집이 주어졌다고 가정하고, 각 군집 별로 지역적인 AAM 모델을 구축하여 정합과정 중에 적합한 모델이 선택되도록 한다. 정합과정에서 발생하는 모델변경에 따른 모델간의 정합 인자 갱신의 문제는 인자 공간에서 모델간의 선형 관계를 미리 학습하여 해결한다. 심각한 정합 실패에 따른 잘못된 모델 선택을 줄이기 위해 점진적으로 모델변경이 이루어지도록 한다. 실험에서는 제안하는 방법을 Yale-B 조명얼굴 영상에 적용하여 모델을 생성하고 기존 방법과 정합 성능을 비교한다. 제안 방법은 심각한 그림자가 발생하는 강도 높은 조명얼굴 영상에서 성공적인 정합 결과를 보여주었다.

In the face space, face images due to illumination and pose variations have a nonlinear distribution. Active Appearance Models (AAM) based on the linear model have limits to the nonlinear distribution of face images. In this paper, we assume that a few clusters of face images are given; we build local AAMs according to the clusters of face images, and then select a proper AAM model during the fitting phase. To solve the problem of updating fitting parameters among the models due to the model changing, we propose to build in advance relationships among the clusters in the parameter space from the training images. In addition, we suggest a gradual model changing to reduce improper model selections due to serious fitting failures. In our experiment, we apply the proposed model to Yale Face Database B and compare it with the previous method. The proposed method demonstrated successful fitting results with strongly illuminated face images of deep shadows.

키워드

참고문헌

  1. T. F. Cootes, C. Taylor, D. Cooper, and J. Graham, 'Active shape models-their training and their applications,' Computer Vision and Image Understanding, vol.61, no.1, pp.38-59, 1995 https://doi.org/10.1006/cviu.1995.1004
  2. T. F. Cootes, D. J. Edwards, and C. J. Taylor, 'Active Appearance Models,' IEEE Trans. on PAMI, vol.23, no.6, pp.681-685, 2001 https://doi.org/10.1109/34.927467
  3. S. Baker and I. Matthews, 'Lucas-Kanade 20 Years On: A Unifying Framework,' Int’l Journal of Computer Vision, vol.56, no.3, pp.221-255, 2004 https://doi.org/10.1023/B:VISI.0000011205.11775.fd
  4. I. Matthews and S. Baker, 'Active Appearance Models Revisited,' Int’l Journal of Computer Vision, vol.60, no.2, pp.135-164, 2004 https://doi.org/10.1023/B:VISI.0000029666.37597.d3
  5. J. Xiao, S. Baker, I. Matthews, and T. Kanade, 'Real-Time Combined 2D+3D Active Appearance Models,' Proc. of IEEE Int'l Conf. on CVPR, vol.2, pp.535-542, 2004 https://doi.org/10.1109/CVPR.2004.201
  6. A. U. Batur and M. H. Hayes, 'Adaptive Active Appearance Models,' IEEE Trans. on Image Processing, vol.14, no.11, pp.1707-1720, 2005 https://doi.org/10.1109/TIP.2005.854473
  7. J. Liebelt, J. Xiao, and Jie Yang, 'Robust AAM Fitting by Fusion of Images and Disparity Data,' Proc. of the IEEE Int'l Conf. on CVPR, vol.2, pp. 2483-2490, 2006 https://doi.org/10.1109/CVPR.2006.255
  8. S. Gong, A. Psarrou, and S. Romdhani, 'Corresponding dynamic appearances,' Image and Vision Computing, vol.20, pp.307-318, 2002 https://doi.org/10.1016/S0262-8856(02)00025-2
  9. Y. Zhou, W. Zhang, X. Tang, and H. Shum, 'A Bayesian Mixture Model for Multi-view Face Alignment,' Proc. of IEEE Int'l Conf. on CVPR, vol.2, pp.741-746, 2005 https://doi.org/10.1109/CVPR.2005.17
  10. S. Baker and I. Matthews, 'Automatic Construction of Active Appearance Models as an Image Coding Problem,' IEEE Trans. on PAMI, vol.26, no.10, pp.1380-1384, 2004 https://doi.org/10.1109/TPAMI.2004.77
  11. C. Hu, R. Feris, and M. Turk, 'Real-time View-based Face Alignment using Active Wavelet Networks,' Proc. of IEEE Int'l Workshop on Analysis and Modeling of Faces and Gestures, pp. 215-221, 2003 https://doi.org/10.1109/AMFG.2003.1240846
  12. M. Uzumcii, A. F. Frangi, M. Sonka, J. H. Reiber, and B.P. Lelieveldt, 'ICA vs. PCA Active Appearance Models: Application to Cardiac MR Segmentation,' LNCS 2878, pp.451-458, 2003
  13. S. Mika, B. Scholkopf, A. Smola, G. Ratsch, K. Muller, M. Scholz, and G. Ratsch, 'Kernel-PCA and De-Noising in Feature Spaces,' Advances in Neural Information Processing Systems, vol.11, pp.536-542, 1999
  14. C. M. Christoudias and T. Darrell, 'On Modeling Nonlinear Shape-and-Texture Appearance Manifolds,' Proc. of the IEEE Int'l Conf. on CVPR, vol.2, pp. 1067-1074, 2005 https://doi.org/10.1109/CVPR.2005.255
  15. C. Butakoff and A. Frangi, 'A Framework for Weighted Fusion of Multiple Statistical Models of Shape and Appearance,' IEEE Trans. on PAMI, vol.28, no.11, 2006 https://doi.org/10.1109/TPAMI.2006.215
  16. R. Bowden, T.A. Mitchell, and M. Sahardi, 'Cluster based non-linear principal component analysis,' IEE Electronics Letters, vol.33, no.22, pp. 1858-1859, 1997 https://doi.org/10.1049/el:19971300
  17. T.F. Cootes, G.V. Wheeler, K.N. Walker, and C.J. Taylor, 'View-based active appearance models,' Image and Vision Computing, vol.20, pp.657-664, 2002 https://doi.org/10.1016/S0262-8856(02)00055-0
  18. Z. Zhang, and J. Wang, 'MLLE: Modified Locally Linear Embedding Using Multiple Weights,' Proc. of Int'l NIPS, vol.19, pp.1618-1625, 2006
  19. K. Sung and T. Poggio, 'Example-Based Learning for View-Based Human Face Detection,' IEEE Trans. on PAMI, vol.20, no.1, pp.39-51, 1998 https://doi.org/10.1109/34.655648
  20. Yale Face Database B: http://cvc.yale.edu/projects/yalefacesB/yalefacesB.html