The skin is the human body’s largest organ and its cancer is considered among the most dangerous kinds of cancer. Various pathological variations in the human body can cause abnormal cell growth due to genetic disorders. These changes in human skin cells are very dangerous. Skin cancer slowly develops over further parts of the body and because of the high mortality rate of skin cancer, early diagnosis is essential. The visual checkup and the manual examination of the skin lesions are very tricky for the determination of skin cancer. Considering these concerns, numerous early recognition approaches have been proposed for skin cancer. With the fast progression in computer-aided diagnosis systems, a variety of deep learning, machine learning, and computer vision approaches were merged for the determination of medical samples and uncommon skin lesion samples. This research provides an extensive literature review of the methodologies, techniques, and approaches applied for the examination of skin lesions to date. This survey includes preprocessing, segmentation, feature extraction, selection, and classification approaches for skin cancer recognition. The results of these approaches are very impressive but still, some challenges occur in the analysis of skin lesions because of complex and rare features. Hence, the main objective is to examine the existing techniques utilized in the discovery of skin cancer by finding the obstacle that helps researchers contribute to future research.

The development of abnormal cell growth is caused by different pathological alterations and some genetic disorders. This alteration in skin cells is very dangerous and life-threatening, and its timely identification is very essential for better treatment and safe cure. Therefore, in the present article, an approach is proposed for skin lesions’ segmentation and classification. So, in the proposed segmentation framework, pre-trained Mobilenetv2 is utilised in the act of the back pillar of the DeepLabv3+ model and trained on the optimum parameters that provide significant improvement for infected skin lesions’ segmentation. The multi-classification of the skin lesions is carried out through feature extraction from pre-trained DesneNet201 with N × 1000 dimension, out of which informative features are picked from the Slim Mould Algorithm (SMA) and input to SVM and KNN classifiers. The proposed method provided a mean ROC of 0.95 ± 0.03 on MED-Node, 0.97 ± 0.04 on PH2, 0.98 ± 0.02 on HAM-10000, and 0.97 ± 0.00 on ISIC-2019 datasets.