A Novel Method for Skin Lesion Segmentation

Skin cancer has been the most usual and illustrates 50% of all new cancers detected each year. If they detected at an early stage, treatment can become simple and economically. Accurate skin lesion segmentation is important in automated early skin cancer detection and diagnosis systems. The aim of this study is to provide an effective approach to detect the skin lesion border on a purposed image. A novel method based on image processing is proposed that combines the edge detection and the thresholding technique for skin lesions detection from skin region in an image. The distributions of edge and the proposed thresholding method provide a good discrimination of skin lesions. The evaluation of the proposed method is based on the comparison with the Otsu and Rosin segmentation as the most application methods. The performance of the designed system is evaluated with 30 test images, and the experimental results demonstrate the effectiveness of the proposed mole localization scheme.

Computer-aided lesion diagnosis; Segmentation; Hair Removal; Median Filter; Boundary Detection; Symmetry