Abstract
Many cases of skin diseases in the world have triggered a need to develop an effective automated screening method for detection and diagnosis of the area of disease. Therefore the objective of this work is to develop a new technique for automated detection and analysis of the skin disease images based on color and texture information for skin disease screening.
In this paper, a study of the role of color information in detecting the edges of images was conducted. Therefore another color space (HIS) is implemented. Several edge detection techniques are applied such as Laplace and Perwitt, the results shows that the Laplace operator is more efficient than Perwitt operator in edge detection. Wavelet Transform plays an important role in the image processing analysis, especially in texture recognition of data. For its fine result when using Multi-resolution modeling. The texture image will be entered to Wavelet Mother Function; this will segment the texture into sub bands. These sub bands contain information about the texture, then this information will be entered to feature extraction, the output from them represent the input to the Artificial Neural Network (ANN) which represents powerful tool for handling problems of large dimension.
The idea of combining wavelets and neural networks is proposed to classify images. The output of ANN represents the type of texture.
