Diabetes Diagnostic Method based on Tongue Image Using ANN & CNN Classifier
E. Srividhya1, A. Muthukumaravel2
1E. Srividhya, Research Scholar, Bharath Institute of Higher Education and Research, Chennai (Tamil Nadu), India.
2Dr. A. Muthukumaravel, Dean Professor & Head, Faculty of Arts & Science, Department of MCA, Bharath Institute of Higher Education and Research, Chennai (Tamil Nadu), India.
Manuscript received on 03 June 2019 | Revised Manuscript received on 28 June 2019 | Manuscript Published on 04 July 2019 | PP: 284-288 | Volume-8 Issue-1S4 June 2019 | Retrieval Number: A10490681S419/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper diagnosing diabetic using tongue image is classified based on the machine learning and deep learning concepts. For machine learning Artificial Neural Network (ANN) and for deep learning Convolution Neural Network (CNN) are used to classify the diabetic patients tongue. There is a strong relationship between the characteristics of tongue and human health diagnosis for any diseases. In this proposed method we are going to get the input image, preprocessing the image for noise reduction and segment the image with size, shape and color, then we have to classify whether that image is diabetic or healthy tongue image. If it is a diabetic image again we have to classify for Diabetic Mellitus types that istype 1 and type 2 based on the severity in the image. The proposed method is compared with SVM classifier for better accuracy. As the experiment results in 98% of accuracy in diagnosing the diabetic diseases.
Keywords: Tongue Image Classification, ANN Classifier, CNN Classifier, Machine Learning Techniques, Deep Learning Techniques.
Scope of the Article: Image Security