Skin Cancer Detection and Classification for Moles Using K-Nearest Neighbor Algorithm

Abstract

The skin protects our body from heat and light of the sun and other threats. One of the illnesses that threaten the skin is the skin cancer. Skin cancer may start with an irregular shaped mole with size greater than a pencil eraser. This study focuses on the non-invasive approach in detecting and classifying skin cancer. Geometrical features of the moles suspected for skin cancer are extracted following the asymmetry, border, and diameter parameters of the ABCD-Rule of Dermoscopy. In particular, greatest and shortest diameter, irregularity index and equivalent diameter are the parameters loaded in the dataset for classification. Classification of mole images is done through k-Nearest Neighbors (k-NN) algorithm. The overall result showed 86.67% accuracy in determining the classification.