SKIN DISEASE DETECTION SYSTEM

Abstract

Skin is the largest organ of the human body. It acts as a shield towards various factors resulting into infections or often diseases. It also holds in the water loss that may happen through the body. Dermatology is a one of major session of medicine that concerns with the diagnosis and treatment of skin diseases. Skin diseases are the most common diseases widespread in humans as well as animals. Even though the disease may seem superficial but negligence may have a lifetime effect on the skin of the patient. Anything that irritates or clogs the skin can cause symptoms such as redness, swelling and itchy skin. Rashes and hives are other signs of skin conditions. Some are quick and easy to treat, while others are chronic or more difficult to get rid of. The presented system is an automated dermatological Diagnostic system. We are going to work on four diseases, Ring worm, herpes, and psoriasis. The system works on two dependent steps - the first detects infected skin patches and the latter identifies the diseases. The system uses visual input i.e. high resolution color Images. It will be used to detect diseases of the skin and offer a treatment recommendation. This system uses technologies such as image processing. The image must be subjected to various pre-processing for noise elimination and enhancement of the image we are going to use classifiers such as LBP, SVM. For disease
classification, the system will resort to feed forward back propagation artificial neural networks. It will be a free process and will not require any special imaging devices as normal cameras shall be sufficient enough to capture the images.