An energy function for facial feature extraction

Human face fiducial points are important features for face recognition and animation. The authors propose an energy function which is the sum of seven weighted terms for facial feature extraction. By allocating different values for the weighting factors, the function can extract different fiducial points. Experimental results show that the proposed method is fast and accurate.

[1]  Roberto Brunelli,et al.  Face Recognition: Features Versus Templates , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Han Huang,et al.  Facial expression morphing and animation with local warping methods , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[3]  Masayuki Nakajima,et al.  Image morphing of facial images transformation based on Navier elastic body splines , 1998, Proceedings Computer Animation '98 (Cat. No.98EX169).

[4]  Thomas S. Huang,et al.  Automatic construction of 3D human face models based on 2D images , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[5]  Yehezkel Yeshurun,et al.  Robust detection of facial features by generalized symmetry , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[6]  Ki-Chung Chung,et al.  Face recognition using principal component analysis of Gabor filter responses , 1999, Proceedings International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems. In Conjunction with ICCV'99 (Cat. No.PR00378).

[7]  A. Martínez,et al.  The AR face databasae , 1998 .

[8]  Zhengyou Zhang,et al.  Comparison between geometry-based and Gabor-wavelets-based facial expression recognition using multi-layer perceptron , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[9]  Ja-Ling Wu,et al.  Automatic facial feature extraction by genetic algorithms , 1998, Electronic Imaging.