Improvements on Search Process and Search Subspace in Active Shape Model
HE Liang-Hua1, HU Die2, JIANG Chang-Jun1
1.School of Electronics and Information Engineering, Tongji University, Shanghai 2000922. Department of Communication Science and Engineering, Fudan University, Shanghai 200433
Abstract The method of active shape model (ASM) is quite commonly used for alignment in recent years. However, its search subspace has a number of limitations on reconstructing the changeable shape in real life. In addition, since there is no restriction during searching, the result is unstable. In this paper, some improvements on search subspace and search process are proposed. By adding eigen-shape variance information to search subspace, the new search subspace can reconstruct the shape more generally. In the meantime, the search errors are analyzed and searching information of the next step is obtained. The whole search processing is iterated and connected with the feedback of search error. The feedback and iteration make the search processing more active and the final search result is unique. Several face alignment experiments are designed and the results show that the proposed method improves alignment precision greatly.
[1] Wiskott L, Fellous J M, Kruger N, et al. Face Recognition by Elastic Bunch Graph Matching. IEEE Trans on Pattern Analysis and Machine Intelligence, 1997, 19(7): 775-779 [2] Kass M, Witkin A, Terzopoulos D. Snakes: Active Contour Models. International Journal of Computer Vision, 1988, 1(4): 321-331 [3] Yuille A L. Deformable Templates for Face Detection. Journal of Cognitive Neuroscience, 1991, 3(1): 59-70 [4] Beymer D. Vectorizing Face Images by Interleaving Shape and Texture Computation. Technical Report, AIM-1537, Cambridge, USA: Massachusetts Institute of Technology, 1995 [5] Cootes T F, Taylor C J, Cooper D H, et al. Active Shape Models: Their Training and Application. Computer Vision and Image Understanding, 1995, 61(1): 38-59 [6] Cootes T F, Edwards G J, Taylor C J. Active Appearance Models. IEEE Trans on Pattern Analysis and Machine Intelligence, 2001, 23(6): 681-685 [7] Blanz V, Vetter T. A Morphable Model for the Synthesis of 3D Faces // Proc of the 26th Annual Conference on Computer Graphics and Interactive Techniques. Los Angeles, USA, 1999: 187-194 [8] Yan Shuicheng, Liu Ce, Li S Z, et al. Face Alignment Using Texture-Constrained Active Shape Models. Image and Vision Computing, 2003, 21(1): 69-75 [9] Zhou Yi, Gu Lie, Zhang Hongjiang. Bayesian Tangent Shape Model: Estimating Shape and Pose Parameters via Bayesian Inference // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Madison, USA, 2003, Ⅰ: 109-116 [10] Li Yuanzhong, Ito W. Shape Parameter Optimization for AdaBoosted Active Shape Model // Proc of the 10th IEEE Conference on Computer Vision. Beijing, China, 2005: 251-258 [11] Zhao Ming, Chen Chun, Li S Z, et al. Subspace Analysis and Optimization for AAM Based Face Alignment // Proc of the 6th IEEE International Conference on Automatic Face and Gesture Recognition. Seoul, Korea, 2004: 290-295 [12] Huang Xiangsheng, Li S Z, Wang Yangsheng. Evaluation of Face Alignment Solutions Using Statistical Learning // Proc of the 6th IEEE International Conference on Automatic Face and Gesture Recognition. Seoul, Korea, 2004: 213-218 [13] Phillips P J, Moon H, Rizvi S A, et al. The FERET Evaluation Methodology for Face-Recognition Algorithms. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(10): 1090-1104 [14] Martinez A, Benavente R. The AR Face Database. Technical Report, 24, Barcelona, Spain: Computer Vision Center (CVC), 1998 [15] Shan Shiguang. Study on Some Key Issues in Face Recognition. Ph.D Dissertation. Beijing, China: Chinese Academy of Sciences. Graduate School, 2004: 38 (in Chinese) (山世光.人脸识别中若干关键问题的研究.博士学位论文.北京:中国科学院研究生院,2004: 38) [16] Li S Z, Zhang Zhenqiu. FloatBoost Learning and Statistical Face Detection. IEEE Trans on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1112-1123
2008, Vol. 21 
