基于权重学习的图像最大权对集匹配模型

Weight setting has a great impact on performance of graph matching models. Weights by direct calculation often produce unsatisfactory correspondences between real images. Based on the idea of learning graph matching for quadratic assignment problems, this paper considers weight learning methods for first- and second-order maximum weight matching models. In a first-order maximum weight matching model, image feature points are regarded as vertices of a bipartite graph, whereas in a second-order maximum weight matching model, edges connecting two feature points are viewed as vertices. Both of the first- and second-order models can be solved by the Kuhn-Munkras algorithm. The first-order maximum weight matching model is essentially equivalent to the linear quadratic assignment problem, but the second-order maximum weight matching model is a new model. Experimental results on the CMU House database show that the second-order maximum weight matching model can totally outperform the first-order maximum weight matching model, and both of them perform better in the case of weight leaning than direct calculation.