一种基于图的交互式目标分割算法

静态图片的编辑中,交互式背景、前景分割的高效性研究有着重大的实际意义。传统的分割方法或是应用图片的纹理(色彩)信息,如Magic Wand,或是利用边界(对比度)信息,如Intelligent Scissors。最近提出的Graph cuts分割算法很好地结合了以上的两种信息。该文将介绍Graph cuts算法以及在该算法基础上改进得到的Grab cut算法。Grab cut算法堪称目前交互式分割方法中分割效果较好的方法,其分割精度高,交互工作少,具有较好的应用前景。文章结合作者当前的研究课题,把Grab cut算法应用在医学图像器官分割中得到了令人满意的效果。

An Interactive Object Segmentation Algorithm Based on Graph

The research of efficiency of interactive foreground/background segmentation in still images is of great practical importance in image editing.Classical image segmentation tools use either texture(color) information,e.g.Magic Wand,or edge(contrast) information,e.g.Intelligent Scissors.Recently,an approach which called graph cuts has been developed successfully combing both types of information.In this paper,it introduces Grab cut which based on Graph cuts and Graph cuts algorithm.Grab cut is the better method in Interactive Segmentation methods,it is accurate and it needs less interactive work.It will be widely used in future.The author combines his research,and uses the Grab cut algorithm in Medical Apparatus segmentation and gets good results.