Abstract: One algorithm，isoperimetric algorithm based on graph theory is applied and researched on image segmentation.Firstly，isoperimetric algorithm is applied in still image segmentation，and the result is compared with two methods based on edge detection and region detection.Then，isoperimetric algorithm is used to segment image video by combined with operation of morphology.Based on several experiments，they are researched.The results show that isoperimetric algorithm can be applied in both still image and image video.Isoperimetric algorithm does well in image segmentation，and it is a fast graph partitioning method.And a good result can be gotten in low contrast image by combined with morphologic operation.

Key words: graph-theory, segmentation, isoperimetric algorithm, morphology

摘要： 采用一种基于图论的等周算法对图像的分割进行了研究。首先利用等周算法对静止图像进行分割，并与边缘检测和区域检测的两种分割方法进行结果比较；接着利用等周算法并结合数学形态学处理对图像序列的分割进行了研究。实验结果表明：等周算法不仅可用于静止图像的分割，也可应用于图像序列的分割。基于等周算法可获取更为精确的分割结果，是一种快速的图论分割方法。并且结合形态学处理可对低对比度的目标获取好的分割结果。

关键词: 图论, 分割, 等周算法, 形态学