Valuable pre-processing and segmentation techniques used in automated skin lesion detection systems

Abstract

The bio-medical investigation from images through computational techniques is very common in these days. Automatic Lesion extraction from skin, is very important to aid the dermatologists in the diagnosis of cancer part from skin. Usually, some skin lesions are very subjective and small, there for not detected by the clinicians by visual examination or sometimes, the clinicians have some problems in their classification. This work presents a comparative study on different techniques to pre-process the lesion image to enhance its readability and the techniques that automatically segment skin lesions from images. Moreover, pros and cons of various methods are also focused to provide a help for the researchers starting work in automated lesion detection system.