[1]张芸凡,徐学军,周赛明,等.一种改进 ROI 模型的舌体红外信息研究[J].计算机技术与发展,2024,34(02):194-200.[doi:10. 3969 / j. issn. 1673-629X. 2024. 02. 028]
　ZHANG Yun-fan,XU Xue-jun,ZHOU Sai-ming,et al.Research for an Improved ROI Model of Tongue Infrared Information[J].,2024,34(02):194-200.[doi:10. 3969 / j. issn. 1673-629X. 2024. 02. 028]
点击复制

一种改进 ROI 模型的舌体红外信息研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年02期
页码:
194-200
栏目:
新型计算应用系统
出版日期:
2024-02-10

文章信息/Info

Title:
Research for an Improved ROI Model of Tongue Infrared Information
文章编号:
1673-629X(2024)02--0194-07
作者:
张芸凡; 徐学军; 周赛明; 杨 刚
长沙理工大学 物理与电子科学学院,湖南 长沙 410114
Author(s):
ZHANG Yun-fan; XU Xue-jun; ZHOU Sai-ming; YANG Gang
School of Physics and Electronic Science,Changsha University of Technology,Changsha 410114,China
关键词:
舌象温度; 葛立恒扫描法; Bezier 曲线; ROI 模型; U-Net 网络模型; 可视化; 舌体信息
Keywords:
tongue temperature; Graham’s scan; Bezier curve; ROI model; U-Net network model; visualization; tongue information
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2024. 02. 028
摘要:
舌诊是中医望诊的重要手段,同时,温度与人体的健康息息相关。 为了研究舌面的脏腑功能定位及舌象温度关系的反映,论文提出了一种红外技术的感兴趣区域( region of interest,ROI)模型研究方法。 首先,利用葛立恒扫描法和 Bezier曲线对多边形 ROI 模型进行改进;然后,借助 U-Net 分割网络将提取出的温度信息进行训练与学习,从而做到批量处理舌体温度信息;最后,利用 HSV 色彩模型进行 3D 可视化,达成舌象温度分区的可视化研究。 此外,为了验证该方法的准确性,实验还对模型截取出的舌体进行了评价指标验证,准确度可以达到 0. 991 1,分割效果极佳。 研究表明:改进后的红外信息提取技术既能直观地观察到舌体的分区状况,也可以完整保留舌体的信息变化,为中医的数据化提供了完整可行性方案。 实现了舌体红外信息数据的提取与中医诊断技术的有机结合。 解决了中医一体化望诊的舌体信息完整性及准确性问题。
Abstract:
Tongue diagnosis is an important tool for Chinese medicine inspection,while temperature is closely related to human health.We propose a region of interest ( ROI) model research method for infrared technology based on the functional localization of the internalorgans on the tongue surface and the reflection of the tongue temperature relationship. Firstly,the polygonal ROI model is improved byusing Graham’s scan method and Bezier curve. Then,the extracted temperature information is trained and learned with the help of U-Net　segmentation network,so as to achieve batch processing of tongue temperature information. Finally,the HSV color model is used for 3Dvisualization to reach the visualization study of tongue temperature partitioning. In addition, in order to verify the accuracy of theproposed method,the experiment also verified the evaluation index of the tongue body truncated by the model,and the accuracy couldreach 0. 991 1,with excellent segmentation effect. The study shows that the improved infrared information extraction technique can notonly visualize the partitioning condition of the tongue body,but also retain the information changes of the tongue body intact, whichprovides a complete feasible solution for the datafication of Traditional Chinese Medicine. The organic combination of extraction ofinfrared information data of the tongue body and Traditional Chinese Medicine diagnosis technology is realized,which solves the problemof completeness and accuracy of the tongue information in the integrated Chinese medicine inspection.
更新日期/Last Update: 2024-02-10