FRACTAL MODEL FOR SKIN CANCER DIAGNOSIS USING PROBABILISTIC CLASSIFIERS
Stalin Jacob, Jenifer Darling Rosita
Abstract
The early detection of skin cancer can lead to high prognosis rate. Thus it is very important to identify abnormalities in skin as early as possible. However, the detection of abnormalities at their early stages is a challenging task since the shape and colour of the abnormalities vary with different persons. In this study, fractal model for skin cancer diagnosis is developed. Differential Box Counting (DBC) method is implemented to get the fractal dimension from the dermoscopic images from two databases; International Skin Imaging Collaboration (ISIC) and PH2 database. The fractal features are classified using a parametric and non-parametric classification approach. The system provides promising results for skin cancer diagnosis with 96.5% accuracy on PH2 images and 91.5% accuracy on ISIC database images using the non-parametric classifier whereas parametric classifier gives 95% (PH2) and 90% (ISIC) images.