• Ashish Limje
• Aishwarya Sawant
• Sonali J. Mane

Using Tongue diagnosis, different diseases that a person carry can be identified. It is one of the methods that is used in Traditional Chinese Medicine (TCM) to diagnose diseases. In addition, being used as a traditional tongue diagnosis method, the model derived by using certain techniques can be used for different purposes such as early disease detection. Therefore, we believe that using the collection of the dataset of different people having diseases as well as persons who are healthy can be very beneficial for analyzing whether a person is healthy or unhealthy. Using methods such as capturing images, extracting features from it can be used to prepare a fulfilled model which will be able to function as we want. A smartphone-based image acquisition device can be proved to be user friendly in terms of simplicity and ease of using the application. Tongue image diagnostic model can identify whether a person is healthy, unhealthy or diabetic based on feature extraction such as texture and color of tongue. The results shows that the system can properly identify three groups of categories such as healthy, unhealthy and diabetic. In this paper we proposed a model based on Convolutional Neural Network and also performed a comparison between Support Vector Machine (SVM) algorithm and Convolutional Neural Network.

Tongue Diagnosis, Machine learning, SVM, Convolutional neural network.

"Tongue Image Analysis for Prediction of Health Quality", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 5, page no.b769-b775, May-2021, Available :http://www.jetir.org/papers/JETIR2105225.pdf

"Tongue Image Analysis for Prediction of Health Quality", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 5, page no. ppb769-b775, May-2021, Available at : http://www.jetir.org/papers/JETIR2105225.pdf