Study on the extraction and analysis methods for color features of cupping plaque images in traditional Chinese medicine

<sec> <title>目的</title> 探索罐斑图像特征信息提取识别及分析方法,构建罐斑图像特征的分类识别模型并提高其分类识别准确性,为后期罐斑作为中医四诊信息的补充和延伸,辅助中医健康状态辨识及疗效评价等提供客观、有效的参考依据,促进中医诊疗规范化、智能化发展。 </sec> <sec> <title>方法</title> 首先利用阈值分割法去除皮肤基底颜色,然后对罐斑进行颜色特征提取,接着采用传统机器学习方法如决策树、支持向量机、最邻近结点算法和极值梯度提升算法,构建罐斑图像颜色分类识别模型,最后利用混淆矩阵进行模型评价,分别得到四种模型的准确率、查准率、查全率和F1分数,加以比较判断。 </sec> <sec> <title>结果</title> 最终选出预测效果最为良好的模型,即XG Boost模型,其准确率为96%,每一类罐斑识别准确率分别为:93%(淡紫)、100%(紫黑)、97%(紫暗)和86%(红)。 </sec> <sec> <title>结论</title> 为中医罐斑的客观识别研究提供了一种新的思路和方法,为辅助中医健康状态辨识和疗效评价提供了客观依据。 </sec>

Authors

Publication Details

Journal
Lishizhen medicine and materia medica research
Published
2025-05-01
DOI
https://doi.org/10.70976/j.1008-0805.szgygy-2025-0932
Primary Topic
Traditional Chinese Medicine Studies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Study on the extraction and analysis methods for color features of cupping plaque images in traditional Chinese medicine

Huilin LIU, Fufeng Li, Bimeng ZHANG, Longbiao Du et al.
Lishizhen medicine and materia medica research
Traditional Chinese Medicine Studies
article

Study on the extraction and analysis methods for color features of cupping plaque images in traditional Chinese medicine

Huilin LIU, Fufeng Li, Bimeng ZHANG, Longbiao Du, Jie Zhao, C. L. Philip Chen, Peng Qian
article en

Abstract

<sec> <title>目的</title> 探索罐斑图像特征信息提取识别及分析方法,构建罐斑图像特征的分类识别模型并提高其分类识别准确性,为后期罐斑作为中医四诊信息的补充和延伸,辅助中医健康状态辨识及疗效评价等提供客观、有效的参考依据,促进中医诊疗规范化、智能化发展。 </sec> <sec> <title>方法</title> 首先利用阈值分割法去除皮肤基底颜色,然后对罐斑进行颜色特征提取,接着采用传统机器学习方法如决策树、支持向量机、最邻近结点算法和极值梯度提升算法,构建罐斑图像颜色分类识别模型,最后利用混淆矩阵进行模型评价,分别得到四种模型的准确率、查准率、查全率和F1分数,加以比较判断。 </sec> <sec> <title>结果</title> 最终选出预测效果最为良好的模型,即XG Boost模型,其准确率为96%,每一类罐斑识别准确率分别为:93%(淡紫)、100%(紫黑)、97%(紫暗)和86%(红)。 </sec> <sec> <title>结论</title> 为中医罐斑的客观识别研究提供了一种新的思路和方法,为辅助中医健康状态辨识和疗效评价提供了客观依据。 </sec>

Lishizhen medicine and materia medica researchVol. 36(9)
Gender equality
Openalex Percentile: Top 70%
Traditional Chinese Medicine Studies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.