European Journal of Molecular & Clinical Medicine

Diabetes people who also take antibiotics to combat different infections are particularly vulnerable to fungal mouth and tongue infection. The fungus prospers in the saliva of uncontrolled diabetes to high glucose levels. An efficient method for Tongue image classification using Non-Negative Matrix Factorization (NNMF) and various Support Vector Machine (SVM) kernels are presented in this study. The input tongue images are given to NNMF for feature extraction and stored in feature database. Finally, SVM kernels like linear, polynomial, quadratic and Radial Basis Function (RBF) are used for prediction. The system produces the classification accuracy of 92% by using NNMF and different SVM kernels

In the day to day working of people, the tongue plays a significant role.The tongue is an organ connected to each other parts.Diabetics classification using tongue images are described in this study. Diabetes detection using tongue image using extraction of texture and random forestis described in this study.Initially, the input tongue images are given to global feature for feature extraction and finally, the decision treeclassifieris used for classification. Experimental results show the performance of proposed system using texture and RFC.