一种基于Graph_Cuts的SAR图像分割方法.pdf

37 卷 5 期 光电工程 Vol.37, No.5 2010 年5 月 Opto-Electronic Engineering May, 2010 文章编号：1003-501X(2010)05-0104-06 一种基于Graph Cuts 的SAR 图像分割方法 陈华杰，吴香伟，薛安克 ( 杭州电子科技大学 信息与控制研究所，杭州 310018 ) 摘要：在最小化由马尔科夫随机场(MRF) 图像分割模型建立的能量函数方面，基于Graph Cuts 的alpha-expansion 是一种比较有效的算法。但是，由此算法构建的s/t 图中边的数目非常多，运算速度很慢。为了减少alpha-expansion 算法的计算量，本文在标号为alpha 的像素向其它像素膨胀的过程中，先隔离非alpha 类间的联系，而只考虑alpha 类与非alpha 类之间的关系，从而避免了alpha-expansion 算法需要构造辅助结点的问题，减少了s/t 图中边的数目， 提高了算法的计算效率。因放松了非alpha 类间的关系对alpha 膨胀的约束，使得算法可以更容易得跳出能量函数 的局部极小点而获得更优的分割结果。实验中将改进的算法与传统的基于Graph Cuts 的算法做了对比，显示了新 算法在运算时间和最小化能量方面的有效性。 关键词：图像分割；能量最小化；Graph Cuts 算法；MRF 模型 中图分类号 TP751.1 献标志码：A doi：10.3969/j. issn.1003-501X.2010.05.019 A New Algorithm Based on Graph Cuts for SAR Image Segmentation CHEN Hua-jie，WU Xiang-wei，XUE An-ke ( Institute of Inf ormation Control, Hangzhou Dianzi University, Hangzhou 310018, China ) Abstract ：Alpha-expansion algorithm based on Graph Cuts is a useful method for minimizing energy function established by Markov Random Field model of image segmentation. However, the number of edge of the graph constructed by the algorithm is large, so the speed is rather slow. In order to reduce the complexity of the alpha-expansion algorithm, the relationship between the pixels labeled alpha and pixels labeled non-alpha was only considered and the relationship between the pixels labeled non-alpha was omitted. This idea avoided adding auxiliary nodes which were one of main factor to affect the efficiency of the alpha-expansion algorithm. Since the constraints on the relationship between pixels set