Abstract: The accuracy of traditional classification method based on remote sensing image is difficult to achieve practical requirements because of remote sensing information uncertainty and the existence of mixed pixel. So Fuzzy C-Means clustering method is analyzed and realized. The researches show the behavior of the FCM clustering depends on the quality of the initialization of the parameters strongly. Remote Sensing Digital Image Fuzzy Clustering based on Gene Expression Programming(RSDIFC-GEP) is proposed and realized. By incorporating the local and global search and taking the clustering result of GEP as the initialized value of the FCM, the algorithm eliminates FCM trapped local optimum and is sensitive to initial value effectively.

Key words: Gene Expression Programming(GEP), remote sensing, digital image, fuzzy clustering

摘要： 针对遥感信息的不确定性和混合像元问题，分析FCM算法。为了避免FCM初值选取不当而陷入局部最优，提出基于基因表达式编程的遥感数字图像模糊聚类算法。该算法可以利用外层GEP算法的全局寻优能力，确定最佳初始聚类中心，再利用内层FCM算法的模糊聚类和局部快速收敛的特性获得遥感数字图像的最优聚类。

关键词: 基因表达式编程, 遥感, 数字图像, 模糊聚类

CLC Number: 

• TP391.41