A METHOD OF SKIN DISEASE DETECTION USING IMAGE PROCESSING

Abstract

Skin diseases are more common than other diseases. Skin diseases may be caused by a fungal infection, bacteria, allergy, viruses etc. The advancement of lasers and photonics-based medical technology has made it possible to diagnose skin diseases much more quickly and accurately. However, the cost of such a diagnosis is very expensive. So, image processing techniques have a role in the diagnosis of skin diseases via an automatic diagnosis system for dermatology at an initial stage. The extraction of features has a major role in the classification of skin diseases. Computer vision has a role in the detection of skin diseases in a variety of techniques. Owing to deserts and hot weather, skin diseases are very common in Saudi Arabia. This study contributes to the research on skin disease detection. We have proposed an image processing-based method to detect skin diseases. This method takes the digital image of disease effect skin area, and uses image analysis to identify the type of disease. Our proposed approach is simple and fast. Most importantly, it does not require expensive equipment other than a camera and a computer. The approach works on the inputs of a color image. The system resizes the input image to extract features using a pre-trained convolutional neural network. After that it classifies feature using multiclass SVM. Finally, the system displays the name of the disease to the user with some tips for the treatment of skin disease. The system detects three different types of skin diseases, namely eczema, psoriasis, and melanoma with a 99% accuracy rate.