A Computer-aided diagnosis system for classifying prominent skin lesions using machine learning

Skin diseases are the 4th leading cause of skin burden worldwide. Computer-aided diagnosis (CAD) systems have been developed to lessen this burden and to help the patients to conduct the early assessment of the skin lesion. Mostly CAD systems available in the literature only provide skin cancer classification. Classification of the skin lesion is a challenging research area due to similar characteristics of skin lesions. A novel CAD system is presented in this research work for the diagnosis of the most common skin lesions (acne, eczema, psoriasis, benign and malignant melanoma). The proposed approach is based on the pre-processing, segmentation, feature extraction and classification phase. Experiments were performed on 1800 images and 83% accuracy is achieved for six-class classification using support vector machine with the quadratic kernel.