Refined SAR image segmentation algorithm based on K-means clustering

Study on SAR image segmentation based on K-means clustering. Analyzes and refined the adaptive moving K-means clustering algorithm by refined the adaptation degree function computation method which dividing the raw adaptation degree function by a direct ratio function of the sample number in clustering and presenting a new sample point separating rule on the clustering area which has the largest adaptation degree function. Millimeter SAR image segment results verify that the refined algorithm have better quality than K-means clustering algorithms in paper for city, road and bridge. Refined K-means clustering algorithm are more efficiency than the adaptive moving K-means clustering algorithm.