Auto-Detection of Skin Cancer

Skin cancer is the most common form of cancers in human; kills people in many parts around world. Every year, more than 68,000 diagnosed as melanoma in USA, and about 80,000 in Canada, and there are 730 states are registered in Iraqi. A physician faces many difficulties for accurate diagnose of lesion through its characteristics and by using the naked eye. For that it is necessary to develop automatic methods in order to increase the accuracy of the diagnostic. In this thesis, two main stages were implemented; the first one is the lesion segmentation while the other stage is the cancer detection. First stage is the lesion segmentation where include edge detection of lesion image based on combination of Markov and Laplace filters, followed by convert image to YUV color space and selected the U channel for processing. Second stage is the lesion diagnoses where achieved by using ABCD rules by suggestion new method for determine asymmetry based on rotation of lesion and divides lesion to two parts once horizontally and later vertically.