Abstract

The skin cancer disease detection and analysis are constrained by human’s visual potential as it entirely depends on microscopic behaviour. The computer-based image reorganization schemes are implemented in accurate classification and identification of skin cancer diseases. Disease Detection operation is performed by k-mean clustering operation on captured real time skin lesion image. Once the detection has been done its features are extracted by Gray Level Co-occurrence Matrix (GLCM) based Texture features; discrete wavelet Transform (DWT) based low level features and Statistical Color features respectively. Generally, classification is done by SVM based approaches, but it is having the low accuracy towards texture features. To implement features based matching operation, an advanced artificial intelligence based Probabilistic Neural Networks (PNN) approach is adopted for classification. The proposed approach is implemented in MATLAB environment, and the accuracy of this methodology is much better that conventional approaches

Description