Graph Based Image Matching
Hui Jiang, Chong‐Wah Ngo · 2004
Given two or more images, we can define different but re-lated problems on pattern matching such as image registra-tion, pattern detection and localization, and common pat-tern discovery. These problems have different levels of pur-pose and difficulties, as a result, often associate with differ-ent solutions. In this paper, we propose a novel approach to solve these problems under a unified framework based on graph matching. We first split the images into small blocks and represent each block as a node in a bipartite graph. A maximum weighted bipartite graph matching algorithm is then employed in an iterative way to find the best trans-formation set. Experimental results show that our approach can handle rotation, scaling and translation, as well as dis-tortion and occlusion. Another virtue of our approach is its efficiency. 1.