Density Based Fuzzy Thresholding for Image Segmentation

Abstract

In this paper, we introduce an image segmentation framework which applies automatic threshoding selection using fuzzy set theory and fuzzy density model. With the use of different types of fuzzy membership function, the proposed segmentation method in the framework is applicable for images of unimodal, bimodal and multimodal histograms. The advantages of the method are as follows: (1) the threshoding value is automatically retrieved thus requires no prior knowledge of the image; (2) it is not based on the minimization of a criterion function therefore is suitable for image intensity values distributed gradually, for example, medical images; (3) it overcomes the problem of local minima in the conventional methods. The experimental results have demonstrated desired performance and effectiveness of the proposed approach. © Springer-Verlag Berlin Heidelberg 2012.