文献类型：期刊文献

英文题名：Maximum Entropy for Image Segmentation based on an Adaptive Particle Swarm Optimization

作者：Qi C.[1]

第一作者：Qi C.

通讯作者：Qi, CM[1]

机构：[1]Beijing Union Univ, Coll Automat, Beijing 100101, Peoples R China

第一机构：北京联合大学城市轨道交通与物流学院

通讯机构：[1]corresponding author), Beijing Union Univ, Coll Automat, Beijing 100101, Peoples R China.|[1141751]北京联合大学城市轨道交通与物流学院;[11417]北京联合大学;

年份：2014

卷号：8

期号：6

起止页码：3129-3135

外文期刊名：APPLIED MATHEMATICS & INFORMATION SCIENCES

收录：;Scopus(收录号：2-s2.0-84904535572);WOS:【SCI-EXPANDED(收录号:WOS:000338123900054)】；

语种：英文

外文关键词：2-D threshold; image segmentation; particle swarm optimization; maximum entropy

摘要：Image segmentation is applied widely to image processing and object recognition. Threshold segmentation is a simple and important method in grayscale image segmentation. Information entropy can characterize the grayscale in formation of image and distinguish between the objectives and background. In this paper, we use exponential entropy instead of logarithmic entropy and propose a new multilevel thresholds image segmentation method based on maximum entropy and adaptive Particle Swarm Optimization (APSO). This proposed algorithm takes full account of the spatial information and the gray information to decrease the computing quantity. The APSO takes advantage of the characteristics of particle swarm optimization, through adaptively adjust particles flying speed to improve evolutional process of basic PSO. Standard test images and remote sensing image are segmented in experiment and compared with other related segmentation methods. Experimental results show that the APSO method can quickly converge with high computational efficiency.