首页 | 本学科首页   官方微博 | 高级检索  
     

基于图割的图像分割方法及其新进展
引用本文:刘松涛,殷福亮.基于图割的图像分割方法及其新进展[J].自动化学报,2012,38(6):911-922.
作者姓名:刘松涛  殷福亮
作者单位:1.大连理工大学电子信息与电气工程学部 大连 116024;
基金项目:中国博士后科学基金(20100471451);水下测控技术国家级重点实验室基金(9140C2603051003)资助~~
摘    要:鉴于图割的理论意义和实际应用价值,系统综述了基于图割的图像分割方法. 首先,深入分析了基于图割的图像分割方法的基本原理,主要从定性和定量角度剖析了图割与能量函数最小化之间的关系, 然后,概括了基于图割的图像分割方法的基本步骤,包括能量函数的设计、图的构造和最小割/最大流方法, 其次,系统梳理和评述了基于图割的图像分割方法的国内外研究现状,最后,指出了基于图割的图像分割方法的发展方向.

关 键 词:图像分割    图割    能量最小化    图论
收稿时间:2011-3-18
修稿时间:2011-7-25

The Basic Principle and Its New Advances of Image Segmentation Methods Based on Graph Cuts
LIU Song-Tao,YIN Fu-Liang.The Basic Principle and Its New Advances of Image Segmentation Methods Based on Graph Cuts[J].Acta Automatica Sinica,2012,38(6):911-922.
Authors:LIU Song-Tao  YIN Fu-Liang
Affiliation:1.Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian 116024;2.Department of Information and Communication Engineering, Dalian Naval Academy, Dalian 116018
Abstract:In view of the theoretical significance and practical value of graph cuts, the image segmentation methods based on graph cuts are reviewed in this paper. Firstly, the basic principle of image segmentation method based on graph cuts is analyzed in detail, which mainly focuses on the relation between graph cuts and energy minimization involving both qualitative and quantitative analysis. Secondly, the steps of image segmentation methods based on graph cuts are generalized as designing energy function, constructing graph, and minimum cut/maximum flow approaches. Thirdly, the current status of image segmentation methods based on graph cuts is combed and commented. Finally, the future for these segmentation methods is pointed out.
Keywords:Image segmentation  graph cuts  energy minimization  graph theory
本文献已被 CNKI 等数据库收录!
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号