ABSTRACT
A recent increase in intelligent Internet of Things (IoT) technologies has led to faster development concerning sensors and automated processes for smart operations. The smart applications focus on the models that eliminate unnecessary actions on the user side while investigating health conditions. Skin lesion segmentation plays a significant part in the earlier diagnosis of skin cancer through automated diagnosis models. The automated detection and classification of the skin lesion is a crucial process due to limitations such as artifacts, unclear boundaries, and diverse shapes of the lesion images. This chapter proposes a novel and effective pipeline for skin lesion segmentation in dermoscopic images. The scale-invariant feature transform-support vector machine (SIFT-SVM) operates using a set of subprocesses namely preprocessing, SIFT-based feature extraction, K-means clustering–based segmentation, and SVM-based classification. The validation of the SIFT-SVM takes place using a skin image data set and the obtained outcome pointed out the effectiveness of the applied model over the compared methods.
