An adaptive clustering segmentation algorithm based on FCM

Abstract

The cluster number and the initial clustering centers must be reasonably set before the analysis of clustering in most cases. Traditional clustering segmentation algorithms have many shortcomings, such as high reliance on the specially established initial clustering center, tendency to fall into the local maximum point, and poor performance with multithreshold values. To overcome these defects, an adaptive fuzzy C-means segmentation algorithm based on a histogram (AFCMH), which synthesizes both main peaks of the histogram and optimized Otsu criterion, is proposed. First, the main peaks of the histogram are chosen by operations like histogram smoothing, merging of adjacent peaks, and filtering of small peaks, and then the values of main peaks are calculated. Second, a new separability measure $\eta $ is defined and a group of main peaks with the maximum value of $\eta $ serve as the optimal segmentation threshold value. The values of these main peaks are employed for initializing of the initial clustering center. Finally, the image is segmented by the weighted fuzzy C-means clustering algorithm. The experiment results show that, compared with existing algorithms, the proposed method not only avoids the oversegmentation phenomenon but also has a significantly shorter computing time than the traditional segmentation algorithm based on mean shift. Therefore, the proposed algorithm can obtain satisfactory results and effectively improve executive efficiency.