基于图匹配理论的图像分割，是IJCV上那片经典文献的作者写的程序，简练实用。可以给做这方面的人的参考-based on the theory of graph matching image segmentation, Shangri-La is IJCV on classic literature written by the author of procedures, concise practical. This can be done to the people of reference

子图像与母图像的匹配（子图像是母图像的一部分），用于判断子图是否在母图中-Sub-image and the master image matching (sub-image is the image part of the mother), used to determine whether the parent graph graph

1.GeometricContext文件是完成图片中几何方向目标分类。 参考文献《Automatic Photo Pop-up》Hoiem 2005 2 GrabCut文件是完成图像中目标交互式分割 参考文献《“GrabCut” — Interactive Foreground Extraction using Iterated Graph Cuts》 C. Rother 2004 3 HOG文件是自己编写的根据HOG特征检测行人的matlab代码 4 虹膜识别程序

代码实现了基于图匹配的分割算法-implementation of graph matching based image segmentation.