Unsupervised Segmentation

Segmentation is the first step in early detection of skin cancer. To analyse, it is necessary to accurately locate and isolate the lesions. In this three unsupervised segmentation method for skin lesions have been discussed. In the Ostu’s method, it has shown the best segmentation results among the three methods. It is fully unsupervised that does not require any change of parameter for different skin lesions. The second one, the gradient vector flow gets in active contour to boundary concavities, even when the noise is present. The execution speed is very slow and that is the drawback. To converge to objects long time is taken. This method is not fully unsupervised. For different skin lesions changing parameters is required. On the other