关键词：图像分割； GomoryHu算法； 聚类； 图论
Fast image segmentation based on GomoryHu algorithm
LIU Bingtao1, TIAN Zheng1,2, ZHOU Qiangfeng1, LI Xiaobin1
（1.Dept. of Applied Mathematics, Northwestern Polytechnical University, Xi’an 710072, China; 2.National Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Applications, Chinese Academy of Sciences, Beijing 100101, China）
GomoryHu algorithm is a classical algorithm for finding the minimum flow and cut equivalent tree of the graph in graph theory, it had the optimal solution. But it was very difficult to deal with large images, and it was biased toward finding small components. In order to solve this problem, this paper presented a novel definition of isolated node, and proposed a novel algorithm based on improved GomoryHu algorithm. This algorithm first used the fast clustering algorithm to reduce the number of vertices ,then used the improved GomoryHu algorithm in the new graph and achieve the optimal solution. Then applied the new algorithm to a number of natural images. The experimental results demonstrate that the algorithm is effective and efficient.......