Unsupervised Learning Technique for Skin Images Segmentation Using a Mixture of Beta Distributions

Abstract

Image segmentation, i.e., identification of homogeneous regions in the image, has been the subject of considerable research activity over the last three decades. Segmentation of images is a major task of image processing. There is no general segmentation procedure that can deal with all sorts of images, and the correct solution will always depend to a certain degree on subjectivity. Many algorithms have been elaborated for gray scale images. Those algorithms are based on different methods including: classification-based methods, edge-based methods, region-based methods, and hybrid methods. Iterative Self-Organizing Data Analysis Technique (ISODATA) is one of the classification-based methods in image segmentation. It is an unsupervised learning Technique. Statistical approach is wieldy used in image processing in order to model the data of image. Gaussian and Gamma distributions have been used in this technique. Gaussian can only approximate a symmetric shape of histogram. Gamma distribution can only approximate a symmetric and a skewed to right shapes of the histogram. However, Beta distribution is more general than Gaussian and Gamma, and it can approximate any shape of histogram as skewed to left, skewed to right, and symmetric. The algorithm developed here is based on the technique of unsupervised learning using a mixture of Beta distributions. Experimental results are presented to show good performance on segmentation of skin images.