Diagnosis of Diabetes by Tongue Analysis

Abstract

Tongue image is used to identify any disease based on its shape, color, size and texture. We proposed the image segmentation method; the segmented study of the tongue reflects the presence of diabetes of a person in addition optimization technique is used to obtain the best result. So in this paper, we are proposing computerized technique to examine the changes in tongue, which will be latter useful in diabetes diagnosis in patients. So initially we take the images of tongue and apply the image processing based on feature extraction technique to extract the two types of features named as, color features and gist features. Later on these quantifies features will be classify by using SOM Kohonen Classifier. The system architecture represents input a image, preprocessing that image, identifying the color, gist feature, implemented and identifies the problem effectively and the result achieved better performance when compared to existing techniques.