Related Experiment Video
Updated: Nov 6, 2025
07:21
Deep Fluorescence Observation in Rice Shoots via Clearing Technology
Published on: June 27, 2022
3.1K
A real-time approach of diagnosing rice leaf disease using deep learning-based faster R-CNN framework
Bifta Sama Bari1, Md Nahidul Islam1, Mamunur Rashid1
1Faculty of Electrical & Electronics Engineering Technology, Universiti Malaysia Pahang, Pekan, Pahang, Malaysia.
Peerj. Computer Science
|May 6, 2021
Summary
This study introduces a Faster R-CNN model for accurate, real-time rice leaf disease detection. The deep learning system achieves high accuracy in identifying common rice diseases, aiding sustainable agriculture.
Area of Science:
- Agricultural Science
- Computer Vision
- Machine Learning
Background:
- Rice leaf diseases threaten global food security and farmer livelihoods.
- Conventional disease diagnosis methods are often slow, inaccurate, and costly.
- Existing computer-assisted systems face challenges like image variability and data scarcity.
Purpose of the Study:
- To develop a robust and efficient system for real-time detection of rice leaf diseases.
- To overcome limitations of traditional diagnosis and current machine-driven approaches.
- To improve the accuracy and speed of identifying critical rice crop infections.
Main Methods:
- Utilized the Faster Region-based Convolutional Neural Network (Faster R-CNN) algorithm.
- Employed an advanced Region Proposal Network (RPN) for precise object localization.
- Trained the model using a combination of online and real-field rice leaf image datasets.
Main Results:
- Achieved high diagnostic accuracies: 98.09% for rice blast, 98.85% for brown spot, and 99.17% for hispa.
- Successfully identified healthy rice leaves with 99.25% accuracy.
- Demonstrated the model's effectiveness in real-time detection of multiple rice diseases.
Conclusions:
- The Faster R-CNN model provides a highly accurate and efficient solution for automated rice leaf disease diagnosis.
- This deep learning approach can significantly enhance sustainable rice production and food security.
- The system offers a precise, real-time tool for identifying common rice crop infections.
