Published Paper Details:

Melanoma is one of the most increasing cancers since past decades. For accurate detection and classification, discriminative features are required to distinguish between benign and malignant cases. Computer vision can play important role in medical image diagnosis and it has been proved by many existing systems. Considering and analysing features of cancer image, which includes Asymmetry, Border irregularity, Compact index, Fractal dimension, Color variation and diameter is popular technique of analysing the patients with skin cancer. To extract and analyse such features, image segmentation plays important role for automatic skin cancer detection system. In this paper we propose the image segmentation scheme based on support vector machine and Convolutional neural network classifier the validated results showed a very encouraging performance with a sensitivity 80.48%, a specificity of 76.19% and accuracy of 98.36% of SVM classifier using linear kernel.