Journals Proceedings

Abstract

Skin cancers are the most common form of cancers in humans [An accurate segmentation of skin images can help the diagnosis to define well the region of the cancer. Image processing techniques has been used for processing the skin cancer images. Image thresholding is an important concept, both in the area of objects segmentation and recognition. This paper proposes a new thresholding method for skin cancer images based on between class variance with a mixture of Gamma distributions. The proposed method estimates the threshold iteratively in order to decrease the running time of the algorithm. The experimental results showed that the new method thresholded well the skin cancer images