Out of the three main kinds of skin cancer—basal cell adenocarcinoma (BCC), squamous cell cancer (SCC), and melanoma—melanoma has the lowest survival rate. Early detection of melanoma may improve patient outcomes. Image processing, which includes shaving, de-noising, sharpening, and resizing the skin picture; segmentation, it is used to segment out the area of interest from the provided image; and resizing are the four main aspects of the skin cancer detection technology. There are several approaches to segmentation. Common segmentation methods include K-means, cutoff in histograms, etc., and then feature extraction from the segmented photograph and categorized the image using the features set returned from the segmented picture. Several different types of categorization methods may do this. Data classification is performed using machine training and deep learning-based algorithms, which have recently been used in skin cancer detection technologies. The most popular classification strategies are the support vector machine (SVM), the feed forward neural network technique (ANN), and the deep convolutional ANN. In this post, we provide findings from our study on cancer of the skin detection, which includes a comprehensive literature review and an in-depth comparison of state-of-the-art algorithms.