Enhance the Alignment Accuracy of Active Shape Models Using Elastic Graph Matching

Active Shape Model (ASM) is one of the most popular methods for image alignment. To improve its matching accuracy, in this paper, ASM searching method is combined with a simplified Elastic Bunch Graph Matching (EBGM) algorithm. Considering that EBGM is too timeconsuming, landmarks are grouped into contour points and inner points, and inner points are further separated into several groups according to the distribution around salient features. For contour points, the original local derivative profile matching is exploited. While for every group of inner points, two pre-defined control points are searched by EBGM, and then used to adjust other points in the same group by using an affine transformation. Experimental results have shown that the proposed method greatly improves the alignment accuracy of ASM with only a little increase of time requirement since EBGM is only applied to a few control points. Keywords Face Alignment, Active Shape Models (ASMs), Active Appearance Models (AAMs), ...

• Type: Conference
• Year: 2004
• Where: ICBA
• Authors: Sanqiang Zhao, Wen Gao, Shiguang Shan, Baocai Yin
• Keywords: Active Shape Models, Biometrics, Elastic Bunch Graph Matching, ICBA 2004, Inner Points