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

Efficacy and safety of Tuina therapy for children with combined allergic rhinitis and asthma syndrome in remission: a randomized controlled trial protocol.

Frontiers in medicine·2026
Same author

Equitable Early Prediction of ICU Length of Stay from First-Day Clinical Data.

Studies in health technology and informatics·2026
Same author

Isoleucyl-tRNA synthetase 1 mutation impairs pulmonary surfactant homeostasis by disrupting alveolar macrophage function.

Respiratory research·2026
Same author

Linking childhood interstitial lung disease to IARS-related disorder: clinical and preliminary functional studies in four new cases.

Human genomics·2026
Same author

Nanotechnology-Based on Natural Medicines: A Promising Alternative for Psoriasis Management.

Current drug delivery·2026
Same author

Research on multi modal corn seed vitality grading based on three branch cross attention fusion network.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026

Related Experiment Video

Updated: Aug 13, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K

Intelligent grading method for walnut kernels based on deep learning and physiological indicators.

Siwei Chen1,2,3, Dan Dai1,2,3, Jian Zheng4

  • 1School of Mathematics and Computer Science, Zhejiang Agriculture and Forestry University, Hangzhou, China.

Frontiers in Nutrition
|January 23, 2023
PubMed
Summary

A new deep learning model using spatial attention and SE-network structures accurately grades walnut kernels. This machine vision approach significantly improves upon traditional methods, achieving 92.2% accuracy for efficient and reliable walnut kernel assessment.

Keywords:
MDA contentsResNet152V2-SA-SEgradingpartitioningswalnut kernels

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.0K
Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research
04:54

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

Published on: November 8, 2024

596

Related Experiment Videos

Last Updated: Aug 13, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.0K
Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research
04:54

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

Published on: November 8, 2024

596

Area of Science:

  • Agricultural technology
  • Computer vision
  • Machine learning

Background:

  • Traditional walnut grading relies on manual assessment, which is inefficient and lacks sophistication, particularly for walnut kernels.
  • Oxidation in walnuts correlates with lightness (L* value) and malondialdehyde (MDA) content, key indicators for quality assessment.

Purpose of the Study:

  • To develop a novel deep-learning model for accurate and efficient machine vision-based grading of walnut kernels.
  • To improve upon existing methods by integrating spatial attention mechanisms and SE-network structures.

Main Methods:

  • Clustering walnut kernels based on L* values and verifying with MDA content to establish grading partitions.
  • Developing and training four deep learning models: VGG19, EfficientNetB7, ResNet152V2, and a combined ResNet152V2-SA-SE model.
  • Optimizing model performance by evaluating learning rates, regularization methods, and batch sizes.

Main Results:

  • The ResNet152V2-SA-SE model achieved the highest test set accuracy of 92.2%, outperforming VGG19, EfficientNetB7, and ResNet152V2.
  • The combined spatial attention and SE network improved target recognition and intrinsic information extraction while reducing focus on irrelevant areas.
  • Optimal training parameters were identified as a learning rate of 0.001, batch size of 128, and no regularization.

Conclusions:

  • The ResNet152V2-SA-SE deep learning model is highly effective for the detection and evaluation of walnut kernels.
  • Machine vision combined with advanced deep learning techniques offers a superior alternative to manual grading for improved accuracy and efficiency.
  • This study provides a robust framework for automated quality assessment in agricultural products.