Method with the center of graph for point pattern matching

Based on the center of graph, a point pattern feature matching method is proposed here. Firstly, a weighted complete graph is constructed with the feature points of each image, and then the center of each graph is found respectively. With the vertex sets of the centers, the feature points are divided into several layers according to the distance from the center, and then the corresponding relation between layers is obtained. Secondly, the Gaussian-weighted Laplace matrices are constructed between the corresponding layers. And then the matrices are submitted to singular-value decomposition (SVD). Finally, represent the feature points with eigenvectors obtained from SVD, and then construct matching matrix to obtain the final matching results. Synthetic data and real world data both indicate that our method has a higher accuracy than theirs, and it can deal with the matching problem with more feature points effectively.