Color image segmentation using automatic thresholding and the fuzzy C-means techniques
Salim Ben Chaabane, Mounir Sayadi, Farhat Fnaiech, É. Brassart · 2008
In this paper, a color image segmentation approach based on automatic histogram thresholding and the fuzzy C-means (FCM) techniques is presented. The originality of this work remains in using thresholding and clustering techniques together for color image segmentation. The histogram considers the occurrence of the gray levels among pixels. In a first stage, the thresholding histogram is used for finding all major homogenous areas. In order to reduce the computational burden required by the fuzzy C-means, the coarse-fine concept methodology is used. The thresholding technique is used for the coarsely segmentation. After the coarse step, and in order to refine further the segmentation of the assigned pixels which remain unclassified, the fuzzy C-means technique is then applied. The experimental results show that the proposed approach can find homogeneous areas effectively, and can solve the problem of discriminating shading in color images to some extent.