Skin Cancer Detection by FCM and Classification of Dermoscopy Images using SVM

Melanoma, one type of skin cancer is considered the most dangerous form of skin cancer occurred in humans. However it is curable if the person detects early. To minimize the demonstrative error affected by the complexity of visual interpretation and subjectivity, it is necessary to develop a technology for computer aided image analysis. This paper presents a methodological approach for the categorization of brunette skin lesions in dermoscopic images. Firstly, the image of the skin to remove unwanted noise and edges, and then the segmentation process is performed to extract the affected area. For detecting the melanoma skin cancer, the GLCM, Thresholding algorithm that segments the lesion from the entire image is used in this study. Feature extraction is then performed by underlying various dermatology rules. After extracting the features from the lesion, feature selection algorithm has been used to get optimized features in order to feed for categorization stage. Fuzzy C-means (FCM) is a method of clustering which allows one piece of data to belong to two or more clusters. Segmentation is performed by using Fuzzy Clustering Means because it has robust characteristics for uncertainty and can retain much more information than hard segmentation methods. Support vector machine has been used as a classifier to classify melanoma and non-melanoma. Experiments have been tested on well-known dataset dermis that is freely available on the Internet. The proposed method has been compared with state of the art methods and shows better performance in comparison to the existing methods.