A novel ensemble deep learning approach for detection and classification of onion diseases

Abstract Ethiopia, highly dependent on agriculture, places significant economic value on onions, a pivotal vegetable crop. However, onion production in Ethiopia faces considerable challenges due to various diseases such as purple blotch, downy mildew, damping off, and the iris yellow spot virus. Cur...

Full description

Saved in:
Bibliographic Details
Main Authors: Asrat Kibret Asnakew, Belay Enyew Chekol, Melaku Bitew Haile, Andargie Geteneh Tegegne, Abebech Jenber Belay
Format: Article
Language:English
Published: Springer 2025-05-01
Series:Discover Applied Sciences
Subjects:
Online Access:https://doi.org/10.1007/s42452-025-06568-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725351093075968
author Asrat Kibret Asnakew
Belay Enyew Chekol
Melaku Bitew Haile
Andargie Geteneh Tegegne
Abebech Jenber Belay
author_facet Asrat Kibret Asnakew
Belay Enyew Chekol
Melaku Bitew Haile
Andargie Geteneh Tegegne
Abebech Jenber Belay
author_sort Asrat Kibret Asnakew
collection DOAJ
description Abstract Ethiopia, highly dependent on agriculture, places significant economic value on onions, a pivotal vegetable crop. However, onion production in Ethiopia faces considerable challenges due to various diseases such as purple blotch, downy mildew, damping off, and the iris yellow spot virus. Current disease management relies on manual inspection methods, leading to variability in effectiveness. In this study, we introduce an ensemble model that extracts and integrates features from VGGNet and AlexNet to classify multiple onion diseases from agricultural onion images. The extracted deep features are then classified using Softmax, k-Nearest Neighbor, Random Forest, and Support Vector Machine classifiers with accuracy of 93%, 75.11%, 94.31%, and 96%, respectively. The model achieved a remarkable accuracy of 96% with the SVM classifier. As a future work, increasing the dataset size and the scope to include other types of onion diseases will improve the robustness and necessity of the model.
format Article
id doaj-art-8d3b5adca9c9447f896f8c10cb3f02c2
institution DOAJ
issn 3004-9261
language English
publishDate 2025-05-01
publisher Springer
record_format Article
series Discover Applied Sciences
spelling doaj-art-8d3b5adca9c9447f896f8c10cb3f02c22025-08-20T03:10:30ZengSpringerDiscover Applied Sciences3004-92612025-05-017511810.1007/s42452-025-06568-3A novel ensemble deep learning approach for detection and classification of onion diseasesAsrat Kibret Asnakew0Belay Enyew Chekol1Melaku Bitew Haile2Andargie Geteneh Tegegne3Abebech Jenber Belay4University of GondarUniversity of GondarUniversity of GondarUniversity of GondarUniversity of GondarAbstract Ethiopia, highly dependent on agriculture, places significant economic value on onions, a pivotal vegetable crop. However, onion production in Ethiopia faces considerable challenges due to various diseases such as purple blotch, downy mildew, damping off, and the iris yellow spot virus. Current disease management relies on manual inspection methods, leading to variability in effectiveness. In this study, we introduce an ensemble model that extracts and integrates features from VGGNet and AlexNet to classify multiple onion diseases from agricultural onion images. The extracted deep features are then classified using Softmax, k-Nearest Neighbor, Random Forest, and Support Vector Machine classifiers with accuracy of 93%, 75.11%, 94.31%, and 96%, respectively. The model achieved a remarkable accuracy of 96% with the SVM classifier. As a future work, increasing the dataset size and the scope to include other types of onion diseases will improve the robustness and necessity of the model.https://doi.org/10.1007/s42452-025-06568-3Onion diseasesEnsemble modelSupport vector machine
spellingShingle Asrat Kibret Asnakew
Belay Enyew Chekol
Melaku Bitew Haile
Andargie Geteneh Tegegne
Abebech Jenber Belay
A novel ensemble deep learning approach for detection and classification of onion diseases
Discover Applied Sciences
Onion diseases
Ensemble model
Support vector machine
title A novel ensemble deep learning approach for detection and classification of onion diseases
title_full A novel ensemble deep learning approach for detection and classification of onion diseases
title_fullStr A novel ensemble deep learning approach for detection and classification of onion diseases
title_full_unstemmed A novel ensemble deep learning approach for detection and classification of onion diseases
title_short A novel ensemble deep learning approach for detection and classification of onion diseases
title_sort novel ensemble deep learning approach for detection and classification of onion diseases
topic Onion diseases
Ensemble model
Support vector machine
url https://doi.org/10.1007/s42452-025-06568-3
work_keys_str_mv AT asratkibretasnakew anovelensembledeeplearningapproachfordetectionandclassificationofoniondiseases
AT belayenyewchekol anovelensembledeeplearningapproachfordetectionandclassificationofoniondiseases
AT melakubitewhaile anovelensembledeeplearningapproachfordetectionandclassificationofoniondiseases
AT andargiegetenehtegegne anovelensembledeeplearningapproachfordetectionandclassificationofoniondiseases
AT abebechjenberbelay anovelensembledeeplearningapproachfordetectionandclassificationofoniondiseases
AT asratkibretasnakew novelensembledeeplearningapproachfordetectionandclassificationofoniondiseases
AT belayenyewchekol novelensembledeeplearningapproachfordetectionandclassificationofoniondiseases
AT melakubitewhaile novelensembledeeplearningapproachfordetectionandclassificationofoniondiseases
AT andargiegetenehtegegne novelensembledeeplearningapproachfordetectionandclassificationofoniondiseases
AT abebechjenberbelay novelensembledeeplearningapproachfordetectionandclassificationofoniondiseases