Comparative Study of Deep Learning Object Detection Methods for Wheat Leaf Disease Detection with Organic Remedy Suggestions - A Review

  • Unique Paper ID: 180198
  • Volume: 12
  • Issue: 1
  • PageNo: 274-278
  • Abstract:
  • The wheat leaf diseases pose a significant threat to global agricultural productivity, necessitating the development of efficient and accurate detection techniques. Recently, development in deep learning (DL) algorithms have completely given new outlook how plant diseases can be detected with the use of object detection models. This review compares leading deep learning (DL) based object detection techniques like Single-Shot Multi-Box Detector (SSD), Convolutional Neural Networks (CNN), Faster R CNN, YOLO version 5 (You Look Only Once), and YOLO version 8 for identifying diseases in wheat leaf. It exhibits comparative study of each model’s mean average precision, architecture, and its speed. Additionally, the review also shows that the likely hood of using organic remedies as a natural and sustainable way to manage plant diseases. While old and traditional chemical treatments are helpful but they lead to environmental impact. As an alternative, organic remedies like biopesticides, neem extracts, and microbial formulations can be effective. The study shows evaluation of the strengths and weaknesses among various detection models in terms of mean average precision, computational cost and real-life disease monitoring. Findings show that YOLOv8 offers both high speed and accuracy, while Faster R-CNN is particularly strong in accuracy. SSD and CNN provide a balanced performance, making them well-suited for environments with limited resources. By integrating deep learning with organic disease control methods, this review promotes a sustainable action to protect wheat crops.

Related Articles