DeepEMPR: coffee leaf disease detection with deep learning and enhanced multivariance product representation

Plant diseases threaten agricultural sustainability by reducing crop yields. Rapid and accurate disease identification is crucial for effective management. Recent advancements in artificial intelligence (AI) have facilitated the development of automated systems for disease detection. This study focu...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmet Topal, Burcu Tunga, Erfan Babaee Tirkolaee
Format: Article
Language:English
Published: PeerJ Inc. 2024-11-01
Series:PeerJ Computer Science
Subjects:
Online Access:https://peerj.com/articles/cs-2406.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846166556320464896
author Ahmet Topal
Burcu Tunga
Erfan Babaee Tirkolaee
author_facet Ahmet Topal
Burcu Tunga
Erfan Babaee Tirkolaee
author_sort Ahmet Topal
collection DOAJ
description Plant diseases threaten agricultural sustainability by reducing crop yields. Rapid and accurate disease identification is crucial for effective management. Recent advancements in artificial intelligence (AI) have facilitated the development of automated systems for disease detection. This study focuses on enhancing the classification of diseases and estimating their severity in coffee leaf images. To do so, we propose a novel approach as the preprocessing step for the classification in which enhanced multivariance product representation (EMPR) is used to decompose the considered image into components, a new image is constructed using some of those components, and the contrast of the new image is enhanced by applying high-dimensional model representation (HDMR) to highlight the diseased parts of the leaves. Popular convolutional neural network (CNN) architectures, including AlexNet, VGG16, and ResNet50, are evaluated. Results show that VGG16 achieves the highest classification accuracy of approximately 96%, while all models perform well in predicting disease severity levels, with accuracies exceeding 85%. Notably, the ResNet50 model achieves accuracy levels surpassing 90%. This research contributes to the advancement of automated crop health management systems.
format Article
id doaj-art-8f1950ce5cc643f4a49e8b844a91173d
institution Kabale University
issn 2376-5992
language English
publishDate 2024-11-01
publisher PeerJ Inc.
record_format Article
series PeerJ Computer Science
spelling doaj-art-8f1950ce5cc643f4a49e8b844a91173d2024-11-15T15:05:15ZengPeerJ Inc.PeerJ Computer Science2376-59922024-11-0110e240610.7717/peerj-cs.2406DeepEMPR: coffee leaf disease detection with deep learning and enhanced multivariance product representationAhmet Topal0Burcu Tunga1Erfan Babaee Tirkolaee2Department of Mathematics Engineering, Istanbul Technical University, Istanbul, TurkeyDepartment of Mathematics Engineering, Istanbul Technical University, Istanbul, TurkeyDepartment of Industrial Engineering, Istinye University, Istanbul, TurkeyPlant diseases threaten agricultural sustainability by reducing crop yields. Rapid and accurate disease identification is crucial for effective management. Recent advancements in artificial intelligence (AI) have facilitated the development of automated systems for disease detection. This study focuses on enhancing the classification of diseases and estimating their severity in coffee leaf images. To do so, we propose a novel approach as the preprocessing step for the classification in which enhanced multivariance product representation (EMPR) is used to decompose the considered image into components, a new image is constructed using some of those components, and the contrast of the new image is enhanced by applying high-dimensional model representation (HDMR) to highlight the diseased parts of the leaves. Popular convolutional neural network (CNN) architectures, including AlexNet, VGG16, and ResNet50, are evaluated. Results show that VGG16 achieves the highest classification accuracy of approximately 96%, while all models perform well in predicting disease severity levels, with accuracies exceeding 85%. Notably, the ResNet50 model achieves accuracy levels surpassing 90%. This research contributes to the advancement of automated crop health management systems.https://peerj.com/articles/cs-2406.pdfPlant diseaseDeep learningEnhanced multivariance product representationHigh dimensional model representation
spellingShingle Ahmet Topal
Burcu Tunga
Erfan Babaee Tirkolaee
DeepEMPR: coffee leaf disease detection with deep learning and enhanced multivariance product representation
PeerJ Computer Science
Plant disease
Deep learning
Enhanced multivariance product representation
High dimensional model representation
title DeepEMPR: coffee leaf disease detection with deep learning and enhanced multivariance product representation
title_full DeepEMPR: coffee leaf disease detection with deep learning and enhanced multivariance product representation
title_fullStr DeepEMPR: coffee leaf disease detection with deep learning and enhanced multivariance product representation
title_full_unstemmed DeepEMPR: coffee leaf disease detection with deep learning and enhanced multivariance product representation
title_short DeepEMPR: coffee leaf disease detection with deep learning and enhanced multivariance product representation
title_sort deepempr coffee leaf disease detection with deep learning and enhanced multivariance product representation
topic Plant disease
Deep learning
Enhanced multivariance product representation
High dimensional model representation
url https://peerj.com/articles/cs-2406.pdf
work_keys_str_mv AT ahmettopal deepemprcoffeeleafdiseasedetectionwithdeeplearningandenhancedmultivarianceproductrepresentation
AT burcutunga deepemprcoffeeleafdiseasedetectionwithdeeplearningandenhancedmultivarianceproductrepresentation
AT erfanbabaeetirkolaee deepemprcoffeeleafdiseasedetectionwithdeeplearningandenhancedmultivarianceproductrepresentation