Home / Current Issue / Paper 1710652
Automated Rice Crop Health Monitoring: A Review of Deep Learning Diseased Leafs Detection and Classification Models
Subject area: Science,Engineering and Technology · Area of research: Deep Learning
DOI: https://doi.org/10.64388/IREV9I3-1710652-392
Abstract
One of the common global vital foods is rice. As important and widespread at it is, it faces significant productivity challenges due to the impact common plant diseases such as bacterial blight, brown spot, and rice blast, which compromise yield and quality in millions of tons worldwide. Relying on manual inspections as a traditional method for disease detection, are often subjective, time-consuming, and subject to errors. The field or Artificial Intelligence in the sub field of deep learning has emerged as a transformative technology for automating disease detection and classification, offering high accuracy and efficiency. This paper provides a comprehensive review of deep learning techniques, including convolutional neural networks, and transfer learning approaches, applied to rice disease detection. Advancements in the design of algorithms, dataset usage, and real-world applications are discussed. Overlapping symptoms, overfitting, and scalability and diverse field conditions are challenges being highlighted, along with proposed solutions. The review emphasizes the need for models that are scalable, diverse datasets, and real-time deployment for practical implementation. Multi-modal systems, lightweight architectures for resource-constrained environments, and integration with precision agriculture systems are the focus for future directions. This work aims to bridge the gap between technological advancements and practical application, contributing to sustainable agricultural practices and global food security.
Keywords
Deep Learning, Convolutional Neural Networks, Transfer Learning, Disease Detection, Disease Classification
How to cite this paper
@article{1710652,
author = {Danladi Shemang Kaje, Prof. A. Y. Gital, Lawal Abdullahi Rukuna, Grace Ojochenemi Emmanuel Anorue, Paul Agada},
title = {Automated Rice Crop Health Monitoring: A Review of Deep Learning Diseased Leafs Detection and Classification Models},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {3},
pages = {745-763},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1710652.pdf},
abstract = {One of the common global vital foods is rice. As important and widespread at it is, it faces significant productivity challenges due to the impact common plant diseases such as bacterial blight, brown spot, and rice blast, which compromise yield and quality in millions of tons worldwide. Relying on manual inspections as a traditional method for disease detection, are often subjective, time-consuming, and subject to errors. The field or Artificial Intelligence in the sub field of deep learning has emerged as a transformative technology for automating disease detection and classification, offering high accuracy and efficiency. This paper provides a comprehensive review of deep learning techniques, including convolutional neural networks, and transfer learning approaches, applied to rice disease detection. Advancements in the design of algorithms, dataset usage, and real-world applications are discussed. Overlapping symptoms, overfitting, and scalability and diverse field conditions are challenges being highlighted, along with proposed solutions. The review emphasizes the need for models that are scalable, diverse datasets, and real-time deployment for practical implementation. Multi-modal systems, lightweight architectures for resource-constrained environments, and integration with precision agriculture systems are the focus for future directions. This work aims to bridge the gap between technological advancements and practical application, contributing to sustainable agricultural practices and global food security.},
keywords = {Deep Learning, Convolutional Neural Networks, Transfer Learning, Disease Detection, Disease Classification},
month = {September},
doi = {https://doi.org/10.64388/IREV9I3-1710652-392}
}