Colour image segmentation using the second order statistics and a modified fuzzy C-means technique

Abstract

This paper presents a new colour image segmentation method based on Fuzzy C-means technique and the second order statistics. The importance of combining statistical features extracted from the co-occurrence matrix and the standard Fuzzy C-Means clustering algorithm in the segmentation context is studied in this paper, to obtain a more reliable and accurate segmentation results. In the first phase of segmentation, a characterization degree is employed to identify the most significant statistical features extracted from the co-occurrence matrix. In the second phase, the Fuzzy C-means (FCM) algorithm is used to cluster the statistical feature vectors into homogeneous regions. Segmentation results from the proposed method are validated and a comparative study versus existing techniques is presented. The experimental results on medical and synthetic colour images demonstrate the superiority of introducing the second order statistics in the Fuzzy C-Means algorithm for colour image segmentation. Key words: Segmentation, medical colour images, fuzzy logic, fuzzy C-Means, second order statistics, co-occurrence matrix.