期刊论文

Tongue Image Segmentation Algorithm Based on Dilated ADU-Net in Open Environment

中文

计算机与现代化

1006-2475

2024

4

48-54

10.3969/j.issn.1006-2475.2024.04.009

2021-896:湖南省一流本科课程项目 kq2202265:长沙市科技局项目 22A0255:湖南省教育厅科学研究重点项目 2020002:湖南省中医药科研计划重点课题

本校为第一机构

舌象的精准分割是能否获得正确舌象诊断结果的重要前提。针对在自然光照条件下传统分割算法难以精确、稳定地分割舌体图像的难题,构建一种融合空洞卷积双注意力机制与密集连接机制的改进型U-Net舌象分割模型(Dilated Att...展开更多 舌象的精准分割是能否获得正确舌象诊断结果的重要前提。针对在自然光照条件下传统分割算法难以精确、稳定地分割舌体图像的难题,构建一种融合空洞卷积双注意力机制与密集连接机制的改进型U-Net舌象分割模型(Dilated Attention&Dense U-Net,Dilated ADU-Net)。首先,基于U-Net网络的对称结构搭建主干网络;然后,下采样模块采用空洞型混合注意力模块,使网络聚焦于舌体...

Accurate tongue image segmentation is an important prerequisite for obtaining correct tongue diagnosis results.Aiming at the problem that traditional segmentation algorithms are difficult to accurately and stably segment tongue images under com⁃plex lighting conditions,...MORE Accurate tongue image segmentation is an important prerequisite for obtaining correct tongue diagnosis results.Aiming at the problem that traditional segmentation algorithms are difficult to accurately and stably segment tongue images under com⁃plex lighting conditions,...