Skin Lesion Classification System Using Shearlets

The main cause of skin cancer is the ultraviolet radiation sun. It spreads quickly to other body parts. Thus, early diagnosis required decrease mortality rate due cancer. In this study, an automatic system for Skin Lesion Classification (SLC) using Non-Subsampled Shearlet Transform (NSST) based energy features and Support Vector Machine (SVM) classifier proposed. At first, NSST used decomposition input lesion images with different directions like 2, 4, 8 16. From NSST’s sub-bands, are extracted stored in feature database training. SVM classification images. dermoscopic obtained from PH2 which comprises 200 color melanocytic lesions. performances SLC evaluated confusion matrix Receiver Operating Characteristic (ROC) curves. achieves 96% accuracy 3rd level 8-directions.