基于区域和统计的彩色图像分割方法,提出了一种结合Voronoi划分技术、最大期望值(EM)和最大边缘概率(MPM)算法的彩色图像分割方法。首先利用Voronoi几何划分将图像域划分成不同的子区域,并假设每个子区域内的像素强度满足独立同一的概率分布,在此基础上建立彩色图像模型;利用上述模型,在贝叶斯理论架构下建模图像分割问题,然后结合EM/MPM算法进行图像分割。该方法将基于像素的马尔可夫随机场(MRF)模型扩展到基于区域的MRF,并且能同时有效地获取模型参数估计和基于区域的彩色图像最优分割。采用本文算法分别对真实彩色图像和合成彩色图像进行分割实验,定性和定量的测试结果验证了本文算法的有效性、可靠性和准确性。

In this paper, we propose a new color image segmentation approach based on the combined use of Voronoi tessellation and the (EM/MPM) algorithm. Voronoi tessellation is a well-established tool for the partition of a geometric region in stochastic geometry theory. Therefore, it is employed for partitioning the image domain into Voronoi polygons corresponding to the components of homogeneous regions that need to be segmented. The EM/MPM algorithm, which integrates the EM algorithm for parameter estimation with the MPM algorithm for segmentation, is also proposed to address color image segmentation. Quantitative experimental results on a synthetic color image show the performance of the proposed approach. Experiments have also been carried out on real world color images in order to validate the proposed approach.