文献类型：期刊文献

英文题名：Tongue Image Texture Classification Based on Image Inpainting and Convolutional Neural Network

作者：Yan, Jianjun[1,2]; Chen, Bochang[2]; Guo, Rui[3]; Zeng, Menghao[1]; Yan, Haixia[3]; Xu, Zhaoxia[3]; Wang, Yiqin[3]

机构：[1] Shanghai Key Laboratory of Intelligent Sensing and Detection Technology, East China University of Science and Technology, Shanghai, 200237, China; [2] Institute of Intelligent Perception and Diagnosis, School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai, 200237, China; [3] Comprehensive Laboratory of Four Diagnostic Methods, Shanghai University of Traditional Chinese Medicine, Shanghai, 201203, China

年份：2022

卷号：2022

外文期刊名：Computational and Mathematical Methods in Medicine

收录：EI(收录号：20230113337396)

语种：英文

外文关键词：Coatings - Convolution - Convolutional neural networks - Diagnosis - Gaussian distribution - Image classification - Textures

摘要：Tongue texture analysis is of importance to inspection diagnosis in traditional Chinese medicine (TCM), which has great application and irreplaceable value. The tough and tender classification for tongue image relies mainly on image texture of tongue body. However, texture discontinuity adversely affects the classification of the tough and tender tongue classification. In order to promote the accuracy and robustness of tongue texture analysis, a novel tongue image texture classification method based on image inpainting and convolutional neural network is proposed. Firstly, Gaussian mixture model is applied to separate the tongue coating and body. In order to exclude the interference of tongue coating on tough and tender tongue classification, a tongue body image inpainting model is built based on generative image inpainting with contextual attention to realize the inpainting of the tongue body image to ensure the continuity of texture and color change of tongue body image. Finally, the classification model of the tough and tender tongue inpainting image based on ResNet101 residual network is used to train and test. The experimental results show that the proposed method achieves better classification results compared with the existing methods of texture classification of tongue image and provides a new idea for tough and tender tongue classification. ? 2022 Jianjun Yan et al.