Diagnostic Model of Gutatte Lesion Utilizing Gaussian RGB Indices through ANN

This paper presents the application of Artificial Neural Network (ANN) in development of an intelligent diagnosis system for selected psoriasis skin disease. Three major types of psoriasis images were captured with controlled environment and analyzed for color feature extraction from Red, Green and Blue(RGB) model. The images would be represented by their gaussian differential mean of each color component where these parameters were trained to produce an optimized ANN model for guttate lesion classification. The optimized ANN model in this work has two methods which based on their gaussian differential mean of RGB and applying sample sized reduced on each pixel gradation values of each image and designed by implementing a multi layer feed forward with back propagation algorithm. Each optimized model are evaluated and validated through analysis of the performance indicators regularly applied in medical research.