![]() ![]() This method addressed the dilemma of lacking tongue color features, but it ignored the disturbing of tongue coat which may influence the accuracy of classification since the tongue image contains both tongue coating and body. implemented the extraction of tongue color and texture fusion features and classification based on the k-nearest neighbor (KNN) classifier AdaBoost algorithm to build fusion features of tough and tender tongue for classification. ![]() Meanwhile, extracting the texture features of the tongue image as a whole as the basis of discriminating the characteristics of tough and tender tongue only achieves the classification of tough and tender tongue, ignoring the case of normal tongue. Only extracting the values describing texture features as the basis of classification makes the description of the characteristics of tough and tender tongue not comprehensive enough, which may affect the classification effect. However, the characteristics of tough and tender tongue essentially contain two parts: color features and texture features. The subimages were classified by using these features. provided an algorithm to get the subimages of the tongue to which gray-level cooccurrence matrix (GLCM) was applied to extract the tongue texture features. used grayscale difference statistics to describe the texture features of the tongue and analyzed the different trends of the four texture parameters in the tough, normal, and tender tongues to recognize tough and tender tongue. Some scholars have already conducted research on the classification of tongue image texture. Therefore, it is necessary to apply modern computer technology to research the classification method of tongue image texture and to realize the objectivity of the classification of tough and tender tongue. ![]() However, nowadays, the clinical diagnosis of tough and tender tongue mainly relies on the physician’s visual observation and subjective judgment, and there is no objective judgment standard. The tough tongue has a rough texture and is firm, which is the main evidence of actuality the tender tongue has a delicate texture and is puffy and delicate, which is the main evidence of deficiency. Tongue diagnosis is one of the important diagnostic tools in traditional Chinese medicine and has great clinical value. ![]() 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. Finally, the classification model of the tough and tender tongue inpainting image based on ResNet101 residual network is used to train and test. 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. Firstly, Gaussian mixture model is applied to separate the tongue coating and body. 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. However, texture discontinuity adversely affects the classification of the tough and tender tongue classification. The tough and tender classification for tongue image relies mainly on image texture of tongue body. Tongue texture analysis is of importance to inspection diagnosis in traditional Chinese medicine (TCM), which has great application and irreplaceable value. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |