Year: 2025
Type: dissertation
Abstract: Early and accurate detection of plant diseases is essential for improving crop yield and ensuring agricultural sustainability.This study proposes a deep learning-based approach for the automated detection and classification of plant diseases using leaf images.A custom Convolutional Neural Network (CNN) architecture is developed and evaluated against two stateof-the-art object detection models-Faster R-CNN and R-FCN.The proposed CNN model is trained and tested on a labeled dataset of diseased and healthy leaf images under varied lighting and background conditions.Performance is assessed using key evaluation metrics including accuracy, precision, recall, and F1-score.Experimental results reveal that the CNN model outperforms the benchmark models, achieving an accuracy of 94.80%, precision of 94.67%, recall of 94.73%, and an F1-score of 94.70%.These results confirm the model's robustness and generalization capability in realworld conditions.The approach offers a low-cost, scalable, and reliable solution for farmers and agricultural experts to identify plant diseases at an early stage, enabling timely intervention and reducing crop losses.This research contributes to the advancement of intelligent agricultural systems by integrating deep learning techniques for plant health monitoring.
Author: Saha, Manish
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: green
OpenAlex ID: W7215313652