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 Experiment Video

Updated: Jul 19, 2026

Computer Vision-Based Biomass Estimation for Invasive Plants
08:47

Computer Vision-Based Biomass Estimation for Invasive Plants

Published on: February 9, 2024

Hybrid deep learning-based multimodal framework for plant leaf disease classification using RGB, Excess Green (ExG),

Saba Begum1, E Naresh2, N N Srinidhi3

  • 1Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India.

Scientific Reports
|May 21, 2026
PubMed
Summary

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

TL-LASSO-Net: a hybrid transfer learning and LASSO-based framework for robust colon cancer histopathology classification on LC25000 and GlaS datasets.

Scientific reports·2026
Same author

A hybrid deep learning model for robust and efficient plant leaf disease detection using ResNet50, PCA, and SVM.

Scientific reports·2026
Same author

AI driven hybrid convolutional and transformer based deep learning architecture for precise lung nodule classification.

Scientific reports·2026
Same author

AI-powered predictive framework for crack detection in steel-copper laser welding.

Scientific reports·2025
Same author

Comprehensive brain tumour concealment utilizing peak valley filtering and deeplab segmentation.

Scientific reports·2025
Same author

Adaptive deep SVM for detecting early heart disease among cardiac patients.

Scientific reports·2025

This study introduces a lightweight deep learning system for plant disease detection, integrating RGB images with synthetic Excess Green (ExG) and pseudo-thermal data. This multimodal approach enhances classification accuracy for improved food security.

Area of Science:

  • Agricultural Science
  • Computer Science
  • Artificial Intelligence

Background:

  • Plant diseases pose a significant threat to global food security, causing reduced crop yields and economic losses.
  • Traditional visual inspection methods for plant diseases are often unreliable due to subjectivity, variable lighting, and environmental unpredictability.

Purpose of the Study:

  • To develop a computationally efficient, lightweight multimodal deep learning system for accurate plant disease classification.
  • To integrate complementary visual representations (Excess Green index and pseudo-thermal) with RGB imagery to overcome limitations of traditional methods.

Main Methods:

  • A multimodal deep learning framework utilizing MobileNetV3-Small backbones for feature extraction and feature-level fusion.
  • Generation of synthetic modalities: Excess Green (ExG) vegetation index and pseudo-thermal representations from RGB images using histogram shifting and pseudo-infrared color mapping.
Keywords:
Excess Green (ExG) vegetation indexGinger Leaf DatasetMobileNetV2Multimodal learningPlant disease detectionPseudo-thermal representations

Related Experiment Videos

Last Updated: Jul 19, 2026

Computer Vision-Based Biomass Estimation for Invasive Plants
08:47

Computer Vision-Based Biomass Estimation for Invasive Plants

Published on: February 9, 2024

  • Experiments conducted on the Ginger Leaf Dataset, employing a stratified 70:15:15 split for training, validation, and testing.

    • Main Results:

    • The multimodal approach, combining RGB with ExG and pseudo-thermal representations, significantly improved plant disease classification performance compared to unimodal RGB models.
    • Ablation studies confirmed the contribution of each modality to the overall classification accuracy.
    • The system demonstrated improved plant disease recognition through the integration of lightweight convolutional neural networks and computationally generated visual representations.

    Conclusions:

    • The proposed lightweight multimodal deep learning system offers an effective and computationally efficient solution for plant disease recognition.
    • Integrating synthetic visual data alongside RGB imagery enhances diagnostic accuracy, contributing to better agricultural outcomes and food security.
    • This approach provides a viable alternative for early and accurate detection of plant diseases without requiring specialized hardware.