Image Segmentation Based on D-S Evidence Theory and C-means Clustering

摘要: On the basis of Dempster-Shafer evidence theory, this paper given multi-source information fusion method based on and applied technology theory in classification bamboo image texture. The data for DS classification, user need to train samples, proposed an D-S automatically obtaining training sample accordance with feature C-means clustering algorithm. First, is divided into several regions, each region containing images using wavelet decomposition remove edge area, then calculate remaining energy mean smooth area as value, use algorithm regional value type samples labeled DS, finally classifier segment image. Experimental results show that has achieved good segmentation results.