SUNet: Coffee Leaf Disease Detection Using Hybrid Deep Learning Model

Leaf mining, rust, bacterial blight, and berry pathology are major diseases in coffee plants. These diseases not only reduce yield but also affect quality. Early detection and targeted treatment are crucial to mitigate their effects. This paper introduces an efficient hybrid deep learning model, SUN...

Full description

Saved in:
Bibliographic Details
Main Authors: Deepak Thakur, Tanya Gera, Ambika Aggarwal, Madhushi Verma, Manjit Kaur, Dilbag Singh, Mohammed Amoon
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10707607/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850282469724520448
author Deepak Thakur
Tanya Gera
Ambika Aggarwal
Madhushi Verma
Manjit Kaur
Dilbag Singh
Mohammed Amoon
author_facet Deepak Thakur
Tanya Gera
Ambika Aggarwal
Madhushi Verma
Manjit Kaur
Dilbag Singh
Mohammed Amoon
author_sort Deepak Thakur
collection DOAJ
description Leaf mining, rust, bacterial blight, and berry pathology are major diseases in coffee plants. These diseases not only reduce yield but also affect quality. Early detection and targeted treatment are crucial to mitigate their effects. This paper introduces an efficient hybrid deep learning model, SUNet, for prediction and classification of healthy and diseased coffee leaves. SUNet integrates U-Net with Segnet’s encoding system, using VGG16 for robust feature extraction. A decoder with skip connections is used to preserve spatial details. Mask R-CNN is also employed for instance segmentation, accurately localizing disease spots. A pyramid pooling module captures multi-scale contextual information. The model is tested using two benchmark datasets, JMuBEN and JMuBEN2. These datasets contain a wide range of coffee leaves affected by phoma, cercospora, or rust, along with healthy samples. SUNet achieved significant performance improvement over other models in terms of accuracy, Intersection over Union (IoU), F1-score, precision, and recall by 1.22%, 1.21%, 1.17%, 1.19%, and 1.24%, respectively. These improvements demonstrate that SUNet can be used for the early detection and classification of coffee leaf diseases. Therefore, with precise and timely interventions, SUNet can help farmers minimize crop losses, enhance coffee production quality, and reduce reliance on harmful chemical treatments.
format Article
id doaj-art-469bd73a551e409fb451dd5437b0362d
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-469bd73a551e409fb451dd5437b0362d2025-08-20T01:47:58ZengIEEEIEEE Access2169-35362024-01-011214917314919110.1109/ACCESS.2024.347621110707607SUNet: Coffee Leaf Disease Detection Using Hybrid Deep Learning ModelDeepak Thakur0Tanya Gera1Ambika Aggarwal2https://orcid.org/0000-0002-6005-2879Madhushi Verma3https://orcid.org/0000-0003-1996-2077Manjit Kaur4https://orcid.org/0000-0001-6259-2046Dilbag Singh5Mohammed Amoon6https://orcid.org/0000-0002-3212-8098Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, IndiaChitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, IndiaDepartment of Computer Science and Engineering, UPES, Dehradun, IndiaSchool of Computer Science Engineering and Technology, Bennett University, Greater Noida, IndiaSchool of Computer Science and Artificial Intelligence, SR University, Warangal, Telangana, IndiaResearch and Development Cell, Lovely Professional University, Phagwara, Punjab, IndiaDepartment of Computer Science, Community College, King Saud University, Riyadh, Saudi ArabiaLeaf mining, rust, bacterial blight, and berry pathology are major diseases in coffee plants. These diseases not only reduce yield but also affect quality. Early detection and targeted treatment are crucial to mitigate their effects. This paper introduces an efficient hybrid deep learning model, SUNet, for prediction and classification of healthy and diseased coffee leaves. SUNet integrates U-Net with Segnet’s encoding system, using VGG16 for robust feature extraction. A decoder with skip connections is used to preserve spatial details. Mask R-CNN is also employed for instance segmentation, accurately localizing disease spots. A pyramid pooling module captures multi-scale contextual information. The model is tested using two benchmark datasets, JMuBEN and JMuBEN2. These datasets contain a wide range of coffee leaves affected by phoma, cercospora, or rust, along with healthy samples. SUNet achieved significant performance improvement over other models in terms of accuracy, Intersection over Union (IoU), F1-score, precision, and recall by 1.22%, 1.21%, 1.17%, 1.19%, and 1.24%, respectively. These improvements demonstrate that SUNet can be used for the early detection and classification of coffee leaf diseases. Therefore, with precise and timely interventions, SUNet can help farmers minimize crop losses, enhance coffee production quality, and reduce reliance on harmful chemical treatments.https://ieeexplore.ieee.org/document/10707607/Agricultural applicationscoffee leaf diseasedeep learningsemantic segmentationSUNetSegNet
spellingShingle Deepak Thakur
Tanya Gera
Ambika Aggarwal
Madhushi Verma
Manjit Kaur
Dilbag Singh
Mohammed Amoon
SUNet: Coffee Leaf Disease Detection Using Hybrid Deep Learning Model
IEEE Access
Agricultural applications
coffee leaf disease
deep learning
semantic segmentation
SUNet
SegNet
title SUNet: Coffee Leaf Disease Detection Using Hybrid Deep Learning Model
title_full SUNet: Coffee Leaf Disease Detection Using Hybrid Deep Learning Model
title_fullStr SUNet: Coffee Leaf Disease Detection Using Hybrid Deep Learning Model
title_full_unstemmed SUNet: Coffee Leaf Disease Detection Using Hybrid Deep Learning Model
title_short SUNet: Coffee Leaf Disease Detection Using Hybrid Deep Learning Model
title_sort sunet coffee leaf disease detection using hybrid deep learning model
topic Agricultural applications
coffee leaf disease
deep learning
semantic segmentation
SUNet
SegNet
url https://ieeexplore.ieee.org/document/10707607/
work_keys_str_mv AT deepakthakur sunetcoffeeleafdiseasedetectionusinghybriddeeplearningmodel
AT tanyagera sunetcoffeeleafdiseasedetectionusinghybriddeeplearningmodel
AT ambikaaggarwal sunetcoffeeleafdiseasedetectionusinghybriddeeplearningmodel
AT madhushiverma sunetcoffeeleafdiseasedetectionusinghybriddeeplearningmodel
AT manjitkaur sunetcoffeeleafdiseasedetectionusinghybriddeeplearningmodel
AT dilbagsingh sunetcoffeeleafdiseasedetectionusinghybriddeeplearningmodel
AT mohammedamoon sunetcoffeeleafdiseasedetectionusinghybriddeeplearningmodel