Layered Graph Matching by Composite Cluster Sampling with Collaborative and Competitive Interactions

This paper studies a framework for matching an unknown number of corresponding structures in two images (shapes), motivated by detecting objects in cluttered background and learning parts from articulated motion. Due to the large distortion between shapes and ambiguity caused by symmetric or cluttered structures, many inference algorithms often get stuck in local minimums and converge slowly. We propose a composite cluster sampling algorithm with a “candidacy graph” representation, where each vertex (candidate) is a possible match for a pair of source and target primitives (local structure or small curves), and the layered matching is then formulated as a multiple coloring problem. Each two vertices can be linked by either a competitive edge or a collaborative edge. These edges indicate the connected vertices should/shouldn’t be assigned the same color. With this representation, the stochastic sampling contains two steps: (i) Sampling the competitive and collabor...

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Kun Zeng, Liang Lin, Song Chun Zhu, Xiaobai Liu
• Keywords: Computer Vision, CVPR 2009, Layered Graph Matching