Research on Skin Cancer Cell Detection Using Image Processing

Out of the three basic types of skin cancer, namely, Basal Cell Carcinoma (BCC), Squamous Cell Carcinoma (SCC) and Melanoma, Melanoma is the most dangerous in which survival rate is very low. Early detection of Melanoma can potentially improve survival rate. The skin cancer detection technology is broadly divided into four basic components, viz., image preprocessing which includes hair removal, de-noise, sharpening, resize of the given skin image, segmentation which is used for segmenting out the region of interest from the given image. Different methods can be used for segmentation. Some commonly used segmentation algorithms are k-means, threshold in histogram etc., features extraction from the segmented image and classification of the image from the features set extracted from segmented image. Different classification algorithms can be used for this purpose. The recent skin cancer detection technology uses machine learning and deep learning based algorithms for classification. The most commonly used classification algorithms are support vector machine (SVM), feed forward artificial neural network, deep convolutional neural network. This paper provides a study and analysis on In this paper, an extensive literature survey of current technology is made for skin cancer detection and an accurate comparison among state of the art algorithm for the same.