Segmentation of skin cancer images using an extension of Chan and Vese model

Recently, more attention is given to automatic detection of cancer. However, the multitude kind of cancer (lung, breast, brain, skin etc.) complicates the detection of this disease with common approaches. An adaptive method for each cancer is the only response to achieve this aim. The segmentation of interest region is the first main step to differentiate between the suspicious and non suspicious part in the image. In this specific work, we focus on a segmentation approach based on Total Variation methods. We propose a generalization of Chan and Vese (CV) model theory and implement it to the particular case of skin cancer images.