Image processing and SVM classification for melanoma detection

Melanoma skin cancer is on the rise globally due to increased ultraviolet radiation and even in darker skinned communities, new cases are being discovered. Like many cancers if detected early the chances of successful treatment and cure are high but if detected at a later stage the chances become low. In the application of Computer Aided Diagnosis systems for detection of melanoma, image pre-processing, segmentation and feature are key stages for accuracy in classification of segmented skin lesions. In this paper, we propose the use of colour space by experimenting with luminance to enhance the visualization for GrabCut segmentation accuracy. We extract geometric and corner features, that are used to train the SVM machine learning algorithm with promising results.