Related Experiment Video
Updated: May 10, 2025
08:47
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
1.2K
Intelligent identification method of origin for Alismatis Rhizoma based on image and machine learning.
Wenqi Zhao1, Zongyi Zhao1, Wen Zheng1
1State Key Laboratory of Southwest Characteristic Chinese Medicine Resources, School of Pharmacy and College of Modern Chinese Medicine Industry, Chengdu University of Traditional Chinese Medicine, Chengdu, 611137, China.
Scientific Reports
|April 22, 2025
Summary
Image analysis accurately identifies the origin of Alismatis Rhizoma (AR), a traditional Chinese medicine. Combining shape, texture features, and the Random Forest model offers a fast, objective method for quality control and source verification.
Area of Science:
- Pharmacognosy
- Computational Biology
- Analytical Chemistry
Background:
- Alismatis Rhizoma (AR) is a widely used traditional medicine with variable quality due to complex origins in China.
- Ensuring AR quality is crucial for clinical efficacy, necessitating objective and rapid source identification methods.
Purpose of the Study:
- To develop and validate a fast, objective method for identifying the species and geographic origins of Alismatis Rhizoma.
- To evaluate the effectiveness of image processing combined with machine learning models for AR authentication.
Main Methods:
- 400 Alismatis Rhizoma samples from two species and four geographic origins were imaged.
- 17 features (3 shape, 2 color, 12 texture) were extracted from images.
- Four classification models (Random Forest, ELM, BP, SVM) were tested using feature combinations.
Main Results:
- The combination of shape (S) and texture (T) features with the Random Forest (RF) model yielded optimal results.
- This S+T-RF approach achieved 99.17% accuracy for species identification and 96.67% for geographic origin identification on test sets.
- The study demonstrated the potential of image processing and RF for complex origin identification.
Conclusions:
- Image processing coupled with the Random Forest model provides a rapid and effective solution for identifying the complex origins of Alismatis Rhizoma.
- This methodology can serve as a valuable reference for authenticating the origins of other medicinal plants.
