A Brief Review of Feature Extraction Methods for Melanoma Detection

One of the most deadly disease on the planet by which numerous individuals lost their lives is melanoma. In the last few decades, melanoma is growing rapidly around the world. In recent years, the fusion of dermoscopy techniques with the CAD system has become an important research field as it helps medical practitioners in gaining meaningful information from images. One of the main stages in any diagnostic system is feature extraction in which selection of the most appropriate feature is a very crucial step. In feature extraction from a single image hundred of features can be extracted. Though, all the extracted features are not suitable for the classification of the lesion. Many features which are not required make the classifier complex and require more computational time, which also reduces the classification accuracy. The best features should represent the characteristic of the region in skin cancer images. To extract the most suitable feature from an image some methods are used. In this paper, a brief review of feature extraction methods developed in the past is discussed.