Abstract In this paper, we try to use graphical model based probabilistic inference methods to solve the problem of contour matching, which is a fundamental problem in computer vision. Specifically, belief propagation is used to develop the contour matching framework. First, an undirected loopy graph is constructed by treating each point of source contour as a graphical node. Then, the distances between the source contour points and the target contour points are used as the observation data, and supplied to this graphical model. During message transmission, we explicitly penalize two kinds of incorrect correspondences: many-to-one correspondence and cross correspondence. A final geometrical mapping is obtained by minimizing the energy function and maximizing a posterior for each node. Comparable experimental results show that better correspondences can be achieved.
Contour Matching Based on Belief Propagation
Computer Vision – ACCV 2006 ; 6 ; 489-498
Lecture Notes in Computer Science ; 3852 , 6
2006-01-01
10 pages
Article/Chapter (Book)
Electronic Resource
English
Hide Node , Belief Propagation , Shape Match , Shape Context , Target Contour Computer Science , Image Processing and Computer Vision , Computer Imaging, Vision, Pattern Recognition and Graphics , Pattern Recognition , Artificial Intelligence (incl. Robotics) , Algorithm Analysis and Problem Complexity
Contour Matching Based on Belief Propagation
British Library Conference Proceedings | 2006
|Acyclic belief propagation for stereo matching
British Library Online Contents | 2009
|Real-time stereo matching based on fast belief propagation
British Library Online Contents | 2012
|Stereo Matching Based on Dissimilar Intensity Support and Belief Propagation
British Library Online Contents | 2013
|Nonparametric belief propagation
IEEE | 2003
|