由于彩色图像提供了比灰度图像更为丰富的信息，因此彩色图像处理正受到人们越来越多的关注。彩色图像分割是彩色图像处理的重要问题，彩色图像分割可以看成是灰度图像分割技术在各种颜色空间上的应用，为了使该领域的研究人员对当前各种彩色图像分割方法有较全面的了解，因此对各种彩色图像分割方法进行了系统论述，即先对各种颜色空间进行简单介绍，然后对直方图阈值法、特征空间聚类、基于区域的方法、边缘检测、模糊方法、神经元网络、基于物理模型方法等主要的彩色图像分割技术进行综述，并比较了它们的优缺点，通过比较发现模糊技术由于能很好地表达和处理不确定性问题，因此在彩色图像分割领域会有更广阔的应用前景。

Due to color image providing more information than monochrome image, color image processing is being paid more and more attention. Image segmentation is critical to image processing and pattern recognition, so all the typical approaches are presented and discussed in this paper. Basically, color image segmentation techniques are based on monochrome ones operating in different color spaces. This paper first reviewed some major color representation methods, then summarized the major color image segmentation approaches including histogram thresholding, characteristic feature clustering, region based approaches, edge detection, fuzzy techniques, neural networks, physics based method. The merits and drawbacks of the methods were discussed too. Fuzzy set theory provides a mechanism to present and manipulate uncertainty and ambiguity, which is desirable for image processing. So, the fuzzy approaches will have a promising application in the color image segmentation area.