Eczema, Hives and Psoriasis Detection with the Application of Local Binary Pattern, Color Histogram, SVM and RGB-HSV Color Space

Abstract

This paper uses a system that can recognize and detect skin diseases such as hives, eczema and psoriasis and provide temporary relief using RGH-HSV Color Space, Local Binary Pattern, Color Histogram and Support Vector Machine (SVM). These algorithms were used to train images for the testing process of the system. For the controlled testing the researchers gathered 30 images for each disease, eczema, hives and psoriasis, from dermnet.com and images from people that have been already diagnosed with the mentioned diseases in both training the prototype and testing the system's accuracy. The system identifying eczema, hives, and psoriasis have the following accuracies respectively, 96.0560%, 95.8041%, and 98.5609%.