Skin cancer is among of most frequent cancer types, with approximately 2 to 3 million cases reported each year globally. Skin cancer is produced by abnormal cell development on the surface of the skin, and physical inspection of skin lesions is a difficult, hard, instinctive, time-consuming process that is prone to inter- and intra-subject variability. For a long time, there has been a need to build a computerized skin diagnostic system to aid doctors in making rapid and prompt decisions. Various academics have suggested a variety of computational intelligence learning models for analyzing skin cancer images, and these models have shown excellent outcomes. However, due to the distinctive and complicated properties of the lesion images, the examination of these skin lesion images using such methodologies currently confronts significant obstacles. The main aim of this study is to review various techniques of preprocessing, segmentation, & classification for the analysis of skin lesions to distinguish between cancerous and non-cancerous images. The main focus is on providing an outline for researchers who are naive to this area and are not equipped to know all of its technical terms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.