Application of Genetic Algorithm Based on Two-dimensional Fuzzy Entropy in SAR Image Segmentation
Honglei Zhang, Jianshe Song, Xianwei Zhang · Jisuanji gongcheng · 2007
【Abstract】The segmentation of target and background is an important content of SAR image segmentation. Threshold method is a kind of simple and practical method. The key problem of threshold segmentation is how to choose appropriate threshold value, and the ordinary method is utilizing grey histogram to get probability distribution density of each grey level, and then choose one or more suitable threshold value according to a certain rule to define adscription of each image pixel. This paper improves the fuzzy entropy method based on two-dimensional histogram, and puts forwards a new segmentation algorithm to seek optimum threshold value in the presence of genetic algorithm. The experimentation shows that it is an effective method for speckled SAR image to segment object and background. 【Key words】Synthetic aperture radar; Genetic algorithm; Fuzzy entropy