Diabetic Detection using Tongue Images Based on ANNClassification
E. Srividhya1, A.Muthukumaravel2

1E.Srividhya, Computer Science, Research Scholar, Bharath Institute of Higher Education and Research, Chennai, India.
2Dr.A. Muthukumaravel, Dean, Faculty of Arts and Science, Bharath Institute of Higher Education and Research, Chennai, India.
Manuscript received on September 22, 2019. | Revised Manuscript received on October 20, 2019. | Manuscript published on October 30, 2019. | PP: 2704-2710 | Volume-9 Issue-1, October 2019 | Retrieval Number: A9750109119/2019©BEIESP | DOI: 10.35940/ijeat.A9750.109119
Open Access | Ethics and Policies | Cite | Mendeley
© 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 work, we proposed an automatic technique to research and detect and examine diabetes through the usage of tongue pix analysis based on Artificial Neural Network (ANN) classifier. There is a sturdy association in between the characteristics of tongue and human health analysis. ANN with a few unique features is used to establish a dating among diseases like diabetes and traits of tongue. Features like Area, Perimeter, Width, Length, Smaller 1/2-distance, Circle Area and Square Area were measured for each tongue. Apart from these Gabor texture features, Hough shape capabilities and color capabilities also extracted. Tongue segmentation is carried out by using the use of vicinity of hobby with shade segmentation. Edge features also extracted the usage of canny facet detection. To compare the overall performance of our proposed approach, we behavior experiments on tongue datasets, wherein ANN technique is applied to classify tongue photographs. The proposed approach is compared with SVM classifier. As the experiment’s consequences proven, our proposed method improves the type accuracy by means of 4.99% on common and achieves 99. Ninety-nine% charter category accuracy.
Keywords: Gabor texture features, tongue images analysis, diabetic analysis, ANN, SVM.