An interactive evolutionary multi-objective approach to skin lesion segmentation

Abstract

In this paper, a generic framework for skin lesion segmentation based on Interactive Evolutionary Computation (IEC) is presented. In this method, a set of segmentation parameters is interactively optimised to produce quality segmentation of skin lesion. Extensive experimental evaluation is carried out on a public dataset of 200 dermoscopic images. The performance of the proposed method is compared to several state-of-the-art techniques in skin lesion segmentation. The results show that the proposed method is superior in providing better segmentation performance.