Computerized tongue coating nature diagnosis using convolutional neural network

Abstract

Tongue coating nature inspection is an essential part in the tongue diagnosis of Traditional Chinese Medicine (TCM). However, it has been depending on doctors' visual judgment. Although many researches have been done in this field, the issue remains challenging. The approaches are limited to image processing or shallow neural networks. In this paper, we propose to computerize tongue coating nature using deep neural networks. The method combines the characteristics of basic image processing and deep learning. A standard and balanced tongue image dataset is used to validate the proposed method.