Diabetes Diagnostic Method based on Tongue Image Using SVM with Gabor Feature
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, Department of Arts & Science MCA, Bharath Institute of Higher Education and Research, Chennai (Tamil Nadu), India.
Manuscript received on 29 May 2019 | Revised Manuscript received on 11 June 2019 | Manuscript Published on 22 June 2019 | PP: 837-842 | Volume-8 Issue-3S, February 2019 | Retrieval Number: C11760283S19/19©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: Tongue diagnosis is an important diagnostic method for evaluating the condition of internal organ by looking at the image of tongue. However, due to its qualitative, subjective and experience-based nature, traditional tongue diagnosis has a very limited application in clinical medicine. Moreover, traditional tongue diagnosis is always concerned with the identification of syndromes rather than with the connection between tongue abnormal appearances and diseases. .In this paper, we present a novel computerized tongue inspection method aiming to address these problems. First, three kinds of features, shape, color and textural measures, are extracted from tongue images by using hough transform, edge detection and gabor filter. Latter on these quantifies features will be classify by using SVM Classifier. Tongue image segmentation is done by using color image segmentation and region of interest. The feature parameters like Area, Perimeter, Width, Length, Smaller half-distance, Circle Area and Square Area have been measured for each tongue in order to obtain the better classification result. Experimental results shows the effectiveness of proposed method. SVM classifier achieves 95 percentage Accuracy.
Keywords: Tongue Image Segmentation, SVM Classifier, Hough Transform, Smaller Half-Distance.
Scope of the Article: Artificial Intelligent Methods, Models, Techniques