Identification of Wheat Leaf Diseases Based on Deep Learning Algorithms

Utilizing a convolutional neural network (CNN) architecture, the proposed method reliably extracts pertinent information from wheat leaf images for disease diagnosis. Preprocessing and data augmentation methods enhance the quality of the wheat-leaf image. CNNs are designed to detect and understand c...

Full description

Saved in:
Bibliographic Details
Published in2023 7th International Conference on Electronics, Communication and Aerospace Technology (ICECA) pp. 721 - 725
Main Authors Therasa, P. R, R, Hemalatha, Sivajothi, E, Jayashankari, J., Princy, B. Anni, S, Uma Maheswari
Format Conference Proceeding
LanguageEnglish
Published IEEE 22.11.2023
Subjects
Convolutional Neural Network
Convolutional neural networks
Crops
Deep learning
Disease Classification
Diseases
Medical diagnosis
Plant Pathology
Training
Transfer learning
Wheat Leaf Disease
Online AccessGet full text

Cover

More Information
Summary:Utilizing a convolutional neural network (CNN) architecture, the proposed method reliably extracts pertinent information from wheat leaf images for disease diagnosis. Preprocessing and data augmentation methods enhance the quality of the wheat-leaf image. CNNs are designed to detect and understand certain characteristics of the images they receive. The network is trained and optimized to classify illnesses more accurately. Standard performance evaluation indicators are utilized to demonstrate the accuracy of wheat leaf disease diagnosis using the suggested technique. Experiments demonstrate that solutions based on deep learning outperform more conventional methods. The proposed work demonstrates how a proposed CNN model outperformed existing techniques by a significant margin (98.31 percent) and how this enhancement would assist in the early diagnosis and treatment of wheat leaf diseases, thereby reducing the likelihood of catastrophic crop loss.
DOI:10.1109/ICECA58529.2023.10395640