Related Experiment Video
Updated: Jun 8, 2026
09:46
Qualitative Identification of Carboxylic Acids, Boronic Acids, and Amines Using Cruciform Fluorophores
Published on: August 19, 2013
16.1K
Chrysanthemum classification via color space fusion transformer
Jian Jiang1, Xichen Yang2, Tianshu Wang3
1School of Computer and Electronic Information /School of Artificial Intelligence, Nanjing Normal University, Nanjing, 210046, Jiangsu Province, China.
Scientific Reports
|February 17, 2026
Summary
Accurate chrysanthemum classification is crucial for its medicinal value. A new Color Space Fusion Transformer method uses RGB and LAB color spaces for cost-effective, real-time identification, achieving 96.16% accuracy.
Area of Science:
- Agricultural Science
- Computer Science
- Biotechnology
Background:
- Chrysanthemum holds significant medicinal and economic importance.
- Accurate classification of chrysanthemum is vital due to variations in medicinal and economic value based on region and type.
- Traditional classification methods are expensive, time-consuming, and labor-intensive, relying on manual, chemical, or genetic analyses.
Purpose of the Study:
- To develop a cost-effective and real-time method for chrysanthemum classification.
- To improve the accuracy and efficiency of identifying chrysanthemum varieties and origins.
- To provide a practical solution for chrysanthemum origin traceability.
Main Methods:
- Proposed a Chrysanthemum Classification via Color Space Fusion Transformer (CC-CSFT) model.
- Images were converted from RGB to LAB color space.
- A multi-path network extracted features from both RGB and LAB spaces, fused them, and a Transformer module analyzed semantic characteristics.
Main Results:
- The proposed CC-CSFT method achieved a classification accuracy of 96.16%.
- Demonstrated superior accuracy and stability compared to existing classification methods.
- The model offers efficient and practical real-time processing capabilities.
Conclusions:
- The Color Space Fusion Transformer provides an efficient and accurate solution for chrysanthemum classification and origin traceability.
- This method overcomes the limitations of traditional approaches, offering a cost-effective alternative.
- The study highlights the potential of advanced computational methods in agricultural product authentication.
