基于Multiscale CNN的齿痕舌识别研究  

Research on teeth-marked tongue recognition based on multiscale convolutional neural network

作　　者：蒋冬梅[1] 杨诺 王勇 彭成东 JIANG Dongmei;YANG Nuo;WANG Yong;PENG Chengdong(Anhui Technical College of Water Resources and Hydroelectric Power,Hefei 231603,China;Hefei Yunzhen Information Technology Co.,Ltd.,Hefei 230088,China)

机构地区：[1]安徽水利水电职业技术学院,安徽合肥231603 [2]合肥云诊信息科技有限公司,安徽合肥230088

出　　处：《安徽水利水电职业技术学院学报》2023年第1期48-51,共4页Journal of Anhui Technical College of Water Resources and Hydroelectric Power

基　　金：安徽高校自然科学研究重大项目(KJ2020ZD77)。

摘　　要：齿痕舌是中医舌诊的一个重要指标。建立的多尺度卷积神经网络由多尺度特征图生成、候选区域搜索、目标区域识别模块组成,实现对轻、中、重3种程度齿痕实例分割与目标区域提取。实验结果表明,齿痕实例分割的精确度高,适用于中医智能舌诊系统应用。Teeth-marked tongue is an important indicator of tongue diagnosis in traditional Chinese medicine.Multiscale convolutional neural network(CNN)model is built,which includes multiscale feature map generation,region proposal searching and target region recognition.As a result,the re-gion instance segmentation of teeth-marked tongue and target region extraction is obtained with light,medium and heavy tooth marks.Results show that the teeth-marked tongue recognition model a-chieved a higher accuracy,which is suitable for the application of the TCM intelligent tongue diagno-sis system.

关 键 词：齿痕识别 实例分割 语义分割 卷积神经网络 深度学习 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]