A Realization of Self-face Diagnosis Algorithm Based on Chinese Medicine Theory

Face recognition is a popular research direction in the field of artificial intelligence. Neural networks are trained on the basis of high-dimensional data characterizing the images to be analyzed and used to extract the important features of the image with the aim of detecting abnormal surface of human faces. The facial anomaly recognition algorithm, which can effectively identify human faces, the acne, moles and dark circles on the face, proposed in this study is realized using the Tensorflow and Keras frameworks. The proposed method has significant application prospects in face diagnosis of Chinese medicine. Experimental studies demonstrated that the proposed method achieves higher recognition accuracy and faster recognition speed in comparison with other existing methods.