关键词: 最大熵, 区域生长, 图像分割

Abstract: Region growing segmentation is a fast and easy algorithm for image segmentation，but it is sensitive to the number of initialization points. An evolutionary region growing segmentation algorithm based on maximum entropy is proposed. The principle of evolutionary maximum entropy is used to calculate the number of regions that are segmented by the evolutionary region. The population is generated according to the number of regions，and the optimal seed and fitness value in each population is calculated and obtained. And then the segmentation of the image is realized. Experimental results show that the algorithm can obtain the image segmentation results more accurately.

Key words: maximum entropy, region growing, image segmentation