Home Journals Articles Updates About
CN
image
收藏切换
Research on Intelligent Image Quality Assessment Method for Juhua（Chrysanthemi Flos）via Deep Color Feature Fusion
收藏切换
Zhongyuan MAO1, Xichen YANG1, Tianshu WANG2, Yifan CHEN1, Jian JIANG1, Hui YAN3, 4
Chinese Archives of Traditional Chinese Medicine | 2026, 44(3) : 13 - 19
Less
收藏切换
Chinese Archives of Traditional Chinese Medicine | 2026, 44(3): 13-19
• Digital Traditional Chinese Medicine •
Research on Intelligent Image Quality Assessment Method for Juhua（Chrysanthemi Flos）via Deep Color Feature Fusion
Full
Zhongyuan MAO1, Xichen YANG1, Tianshu WANG2, Yifan CHEN1, Jian JIANG1, Hui YAN3, 4
Affiliations
  • 1.School of Computer and Electronic Information/School of Artificial Intelligence, Nanjing Normal University, Nanjing 210046, Jiangsu, China
  • 2.College of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210023, Jiangsu, China
  • 3.National and Local Collaborative Engineering Center of Chinese Medicinal Resources Industrialization and Formulae Innovative Medicine, Nanjing 210023, Jiangsu, China
  • 4.Jiangsu Collaborative Innovation Center of Chinese Medicinal Resources Industrialization, Nanjing University of Chinese Medicine, Nanjing 210023, Jiangsu, China
Published: 2026-03-10 doi: 10.13193/j.issn.1673-7717.2026.03.003
Outline
收藏切换
Objective

High quality images of Chinese herbal medicine can effectively ensure the performance of relevant intelligent algorithms. Designing a quality assessment method of Juhua（Chrysanthemi Flos）image to intelligently screen the images that meet the requirements of application scenarios can provide high practical value.

Methods

This research focused on Juhua（Chrysanthemi Flos）. Firstly, it constructed a distorted Juhua（Chrysanthemi Flos）image dataset. And then, it proposed a quality assessment method of Juhua（Chrysanthemi Flos）image based on the deep color feature fusion. In this method, the original Juhua（Chrysanthemi Flos）image was converted from the RGB color space to the HSV color space and Lab color space. The image features of the S color channel, L color channel and b color channel were extracted separately, and the extracted image features were preprocessed. After that, both the preprocessed image features and the original Juhua（Chrysanthemi Flos）image were used as the inputs to a two-stream network to form the fused feature that described the quality of the Juhua（Chrysanthemi Flos）image.

Results

The experimental results demonstrated the rationality of the constructed Juhua（Chrysanthemi Flos）dataset, and the proposed method performed excellently on the distorted Juhua（Chrysanthemi Flos）image dataset, with SROCC and PLCC values reaching above 0.90, and the evaluation results of Juhua（Chrysanthemi Flos）images were highly consistent with the real results.

Conclusion

The method can accurately measures the angular deviation and incomplete distortion of Juhua（Chrysanthemi Flos）in the images, meeting the requirements for intelligent screening of Juhua（Chrysanthemi Flos）images.

Juhua（Chrysanthemi Flos）  /  color space  /  intelligent assessment  /  multi channel network  /  feature fusion
毛忠原, 杨曦晨, 王天舒, 陈奕帆, 蒋健, 严辉. 基于深度颜色特征融合的菊花药材智能评价方法研究. 中华中医药学刊, 2026 , 44 (3) : 13 -19 . DOI: 10.13193/j.issn.1673-7717.2026.03.003
Zhongyuan MAO, Xichen YANG, Tianshu WANG, Yifan CHEN, Jian JIANG, Hui YAN. Research on Intelligent Image Quality Assessment Method for Juhua（Chrysanthemi Flos）via Deep Color Feature Fusion[J]. Chinese Archives of Traditional Chinese Medicine, 2026 , 44 (3) : 13 -19 . DOI: 10.13193/j.issn.1673-7717.2026.03.003
Appendix
Less
Year 2026 volume 44 Issue 3
79
15
Cite this Article
BibTeX
Article Info
doi: 10.13193/j.issn.1673-7717.2026.03.003
  • Online Date：2026-10-14
  • Published：2026-03-10
Article Data
Affiliations
History
Funding
Affiliations
    1.School of Computer and Electronic Information/School of Artificial Intelligence, Nanjing Normal University, Nanjing 210046, Jiangsu, China
    2.College of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210023, Jiangsu, China
    3.National and Local Collaborative Engineering Center of Chinese Medicinal Resources Industrialization and Formulae Innovative Medicine, Nanjing 210023, Jiangsu, China
    4.Jiangsu Collaborative Innovation Center of Chinese Medicinal Resources Industrialization, Nanjing University of Chinese Medicine, Nanjing 210023, Jiangsu, China
References
Share
https://castjournals.cast.org.cn/joweb/zhzyyxk/EN/10.13193/j.issn.1673-7717.2026.03.003
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House