Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A Deep-Learning-Based CPR Action Standardization Method.

Sensors (Basel, Switzerland)·2024
Same author

ISLS: An Illumination-Aware Sauce-Packet Leakage Segmentation Method.

Sensors (Basel, Switzerland)·2024
Same author

Microscopic image recognition of diatoms based on deep learning.

Journal of phycology·2023
Same author

NRVC: Neural Representation for Video Compression with Implicit Multiscale Fusion Network.

Entropy (Basel, Switzerland)·2023
Same author

An Optimized Black-Box Adversarial Simulator Attack Based on Meta-Learning.

Entropy (Basel, Switzerland)·2023
Same author

Blood Glucose Prediction Method Based on Particle Swarm Optimization and Model Fusion.

Diagnostics (Basel, Switzerland)·2022

Related Experiment Video

Updated: Jan 10, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.4K

A Progressive Feature Learning Network for Cordyceps sinensis Image Recognition.

Shangdong Liu1, Wenxiang Wu1, Haijun Chen2

  • 1School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China.

Sensors (Basel, Switzerland)
|November 27, 2025
PubMed
Summary

This study introduces a new AI method, the Progressive Feature Learning Network (PFL-Net), for accurate Cordyceps sinensis (C. sinensis) subspecies recognition. PFL-Net achieves high accuracy, overcoming challenges posed by similar subspecies morphology.

Keywords:
Cordyceps sinensisfeature miningimage recognitionprogressive learning

More Related Videos

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.4K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Related Experiment Videos

Last Updated: Jan 10, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.4K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.4K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Area of Science:

  • Botany
  • Computer Science
  • Machine Learning

Background:

  • Cordyceps sinensis (C. sinensis) is a valuable herbal medicine.
  • Automated recognition of C. sinensis subspecies is difficult due to high morphological similarity and limited phenotypic variation.

Purpose of the Study:

  • To develop a novel approach for automated, fine-grained recognition of C. sinensis subspecies.
  • To improve the accuracy and integrity of C. sinensis recognition by mining multiple biological features.

Main Methods:

  • Proposed the Progressive Feature Learning Network (PFL-Net) incorporating Spatial-aware Semantic Refinement Module (SSRM) and Multi-scale Collaborative Perception Module (MCPM).
  • Introduced a Channel Decouple (CD) loss to enhance feature diversity.
  • Constructed a C. sinensis dataset (CSD) for biometric recognition.

Main Results:

  • The PFL-Net achieved a top-1 accuracy of 94.43% on the CSD dataset.
  • The proposed method surpassed all existing approaches on the CSD and three benchmark datasets.
  • SSRM and MCPM effectively captured multi-scale discriminative features and enhanced recognition integrity.

Conclusions:

  • The PFL-Net demonstrates superior performance in fine-grained C. sinensis subspecies recognition.
  • The novel modules and CD loss contribute to enhanced feature learning and diversity.
  • This work provides a robust solution for C. sinensis biometric recognition and lays the foundation for future research.