A skin disease is a kind of illness caused by bacteria, an infection or radiation. These diseases have various dangerous effects on the skin and keep on spreading over time. It becomes important to identify these diseases at their initial stage to control it from spreading. The traditional diagnosis technique for skin diseases comprised of a recording of what the human eye can see using a digital camera. Such a system is often prone to errors. The proposed idea aims at improving the quality of diagnostic systems by using Image Processing techniques and classification techniques. The proposed system various pre-processing techniques such as resizing, RGB to LAB conversion and contrast enhancement are used. Image segmentation is performed using watershed algorithm. Feature extraction is performed using Grey Level Co-occurrence Matrix (GLCM). Skin diseases are classified as Melanoma, Eczema and Leprosy, using Decision Tree algorithm.
