本文提出一个基于改进谱系聚类法和遗传算法的图像分割方法:根据图像灰度分布的区域一致性的分割思想, 先利用改进的模式识别中的谱系聚类法对图像做指定阈值的聚类分割;并通过计算适应度对不同的指定闲值对应的分割结果做出评价分析;最后充分利用遗传算法优异的全局搜索能力,调整阈值,以取得最优的结果。 In this paper, an image segmentation method based on improved pedigree clustering and genetic algorithm is proposed. According to the segmentation idea of ​​regional consistency of image gray distribution, the clustering method of pedigree in improved pattern recognition Segmentation, and through the calculation of fitness for different assigned idle values ​​corresponding to the segmentation results to make an evaluation analysis; finally make full use of genetic algorithm excellent global search ability, adjust the threshold to obtain the optimal results.