Complexion Classification Based on Convolutional Neural Network

Abstract

Traditional Chinese medicine (TCM) has proved that the complexion of the human body is closely related to the health of each organ, and some visual features of the face can provide valuable clues for the diagnosis of diseases. This paper makes an attempt to develop an automated facial complexion classification model for objective TCM facial diagnosis based on convolutional neural network, and compared it with the existing and traditional machine learning facial classification methods, which has certain reference significance for the future development of deep learning algorithm in the field of TCM.