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 7, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Enhanced rice leaf disease classification via contour-driven segmentation and optimized deep transfer learning

Ummer Shakeel1, Muhammad Asif Habib2, Muhammad Yasir3

  • 1Department of Computer Science, University of Engineering and Technology Taxila, Taxila, Pakistan.

Plos One
|May 7, 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

A Review of Contact Lens-Associated Infections and Biomaterial-Based Solutions.

ACS infectious diseases·2026
Same author

Interplay between CARD9 genetic variants and fungal colonization patterns among patients with diabetes.

Frontiers in fungal biology·2026
Same author

Lightweight and Energy-Aware Intrusion Detection for Industrial IoT Using TinyML and Edge AI.

Scientific reports·2026
Same author

Synergistic Coupling of Iron Single Atoms and Nanoscale Clusters for Enhanced Nitrate Electroreduction to Ammonia.

ChemSusChem·2026
Same author

Tumor CTR1 Expression and Systemic Copper Dynamics Converge on a Copper Axis in High-Grade Triple-Negative Breast Cancer.

Cancer research communications·2026
Same author

Transcriptomic and physiological evidence for magnolol antifungal activity against fusarium oxysporum f. sp. cubense tropical race 4.

Pesticide biochemistry and physiology·2026

Deep learning models accurately detect rice leaf diseases, with InceptionV3 showing the most stable performance. This computer vision approach aids Pakistan

Area of Science:

  • Agricultural Science
  • Computer Vision
  • Machine Learning

Background:

  • Rice cultivation in Pakistan faces challenges in timely disease detection due to manual monitoring.
  • Automated plant health management systems are crucial for efficient disease control in large-scale agriculture.

Purpose of the Study:

  • To develop and evaluate deep learning models for accurate rice leaf disease identification.
  • To compare the performance of various deep transfer learning architectures for disease classification.
  • To enhance model interpretability using segmentation techniques for disease localization.

Main Methods:

  • A dataset of 1914 rice leaf images was processed using Python, TensorFlow, and GPU acceleration.
  • Five deep transfer learning architectures (InceptionV3, DenseNet201, ResNet152V2, EfficientNetV2L, MobileNetV2) were trained and evaluated.

Related Experiment Videos

Last Updated: Jul 7, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

  • GrabCut segmentation and contour detection were employed for interpretable disease localization.

    • Main Results:

    • All evaluated models demonstrated high accuracy in detecting rice diseases.
    • InceptionV3 achieved the most stable performance with 98.43% test accuracy and strong generalization.
    • MobileNetV2 showed reliable performance with lower computational complexity, while EfficientNetV2L had lower accuracy.

    Conclusions:

    • Deep transfer learning is effective for accurate and practical rice disease detection.
    • InceptionV3 is identified as the most stable and efficient model for this application.
    • Explainable AI methods, like GrabCut segmentation, improve understanding of disease identification.