论文信息 - Research on an Improved Active Shape Models

Research on an Improved Active Shape Models

Active shape models (ASM) is one of powerful tools for feature extraction. A new method to construct local appearance model is developed using the information of neighbor landmark points in this paper. This improved method is evaluated on ORL face database, and the experimental results show that the improved ASM improves the accuracy of features extraction.

Yuan Liu | Qingyan Liu | Yuan Liu | Qingyan Liu

[1] Mikkel B. Stegmann,et al. Active appearance models: Theory and cases , 2000 .

[2] Jyh‐Yeong Chang,et al. Automated facial expression recognition system using neural networks , 2001 .

[3] Nicholas Ayache,et al. Fast segmentation, tracking, and analysis of deformable objects , 1993, 1993 (4th) International Conference on Computer Vision.

[4] H. Deutsch. Principle Component Analysis , 2004 .

[5] Timothy F. Cootes,et al. Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[6] Haim J. Wolfson,et al. Articulated object recognition, or: how to generalize the generalized Hough transform , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7] Calyampudi R. Rao,et al. Linear statistical inference and its applications , 1965 .

[8] Demetri Terzopoulos,et al. Snakes: Active contour models , 2004, International Journal of Computer Vision.

[9] Calyampudi Radhakrishna Rao,et al. Linear Statistical Inference and its Applications , 1967 .

[10] C. Goodall. Procrustes methods in the statistical analysis of shape , 1991 .

[11] Alejandro F. Frangi,et al. Active Shape Models with Invariant Optimal Features (IOF-ASMs) , 2005, AVBPA.

[12] K. Mardia,et al. Statistical Shape Analysis , 1998 .

[13] D. Zhang,et al. Principle Component Analysis , 2004 .