Face Alignment Using Active Shape Model And Support Vector Machine

The Active Shape Model (ASM) is one of the most popular local texture models for face alignment. It applies in many fields such as locating facial features in the image, face synthesis, etc. However, the experimental results show that the accuracy of the classical ASM for some applications is not high. This paper suggests some improvements on the classical ASM to increase the performance of the model in the application: face alignment. Four of our major improvements include: i) building a model combining Sobel filter and the 2-D profile in searching face in image; ii) applying Canny algorithm for the enhancement edge on image; iii) Support Vector Machine (SVM) is used to classify landmarks on face, in order to determine exactly location of these landmarks support for ASM; iv)automatically adjust 2-D profile in the multi-level model based on the size of the input image. The experimental results on Caltech face database and Technical University of Denmark database (imm_face) show that our proposed improvement leads to far better performance.

[1]  Harry Shum,et al.  Face alignment using texture-constrained active shape models , 2003, Image Vis. Comput..

[2]  Qiang Wu,et al.  SVM based ASM for facial landmarks location , 2008, 2008 8th IEEE International Conference on Computer and Information Technology.

[3]  Ralph Gross,et al.  Active appearance models with occlusion , 2006, Image Vis. Comput..

[4]  J. Gower Generalized procrustes analysis , 1975 .

[5]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[6]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[7]  Tim Cootes,et al.  An Introduction to Active Shape Models , 2000 .

[8]  Chi Fang,et al.  Generic face alignment using an improved Active Shape Model , 2008, 2008 International Conference on Audio, Language and Image Processing.

[9]  Jie Yang,et al.  Facial feature localization based on an improved active shape model , 2008, Inf. Sci..

[10]  Timothy F. Cootes,et al.  Face Recognition Using Active Appearance Models , 1998, ECCV.

[11]  Xinbo Gao,et al.  Gabor texture in active appearance models , 2009, Neurocomputing.

[12]  Timothy F. Cootes,et al.  Statistical models of appearance for computer vision , 1999 .

[13]  Fred Nicolls,et al.  Locating Facial Features with an Extended Active Shape Model , 2008, ECCV.

[14]  Kin-Man Lam,et al.  An accurate active shape model for facial feature extraction , 2004, Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004..

[15]  Nabeel Tahir,et al.  INTERNATIONAL JOURNAL OF BIOMETRICS AND BIOINFORMATICS (IJBB) , 2011 .

[16]  Anil K. Jain,et al.  Handbook of Face Recognition, 2nd Edition , 2011 .