Support Vector Machine (SVM) for Tomato Leaf Disease Detection

Tomatoes rank among the top five most globally demanded crops and serve as a key ingredient in numerous dishes. However, productivity may decline due to challenges such as diseases, pest infestations, and climate change. Therefore, automatic disease detection is essential to identify early signs of...

Full description

Saved in:
Bibliographic Details
Main Authors: Shafaf Ibrahim, Nur Afiqah Mohd Fuad, Nor Azura Md Ghani, Raihah Aminuddin, Budi Sunarko
Format: Article
Language:English
Published: Universitas Brawijaya 2025-05-01
Series:AGRIVITA Journal of Agricultural Science
Subjects:
Online Access:https://agrivita.ub.ac.id/index.php/agrivita/article/view/3746
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849688600260640768
author Shafaf Ibrahim
Nur Afiqah Mohd Fuad
Nor Azura Md Ghani
Raihah Aminuddin
Budi Sunarko
author_facet Shafaf Ibrahim
Nur Afiqah Mohd Fuad
Nor Azura Md Ghani
Raihah Aminuddin
Budi Sunarko
author_sort Shafaf Ibrahim
collection DOAJ
description Tomatoes rank among the top five most globally demanded crops and serve as a key ingredient in numerous dishes. However, productivity may decline due to challenges such as diseases, pest infestations, and climate change. Therefore, automatic disease detection is essential to identify early signs of illness during the growth period. This study proposes a method for detecting tomato leaf diseases using image processing techniques. The approach involves image enhancement, feature extraction, and classification. Initially, leaf disease images were enhanced using the Contrast Adjustment technique. Subsequently, color and texture features were extracted using Color Moments and the Gray-Level Co-occurrence Matrix (GLCM), respectively. Disease detection was carried out using a Support Vector Machine (SVM). The method was tested on 50 images each for healthy leaves and four types of tomato leaf diseases: Bacterial Spot, Yellow Leaf Curl Virus, Early Blight, and Late Blight. The performance of the disease detection system was evaluated using a confusion matrix, achieving an overall accuracy, sensitivity, and specificity of 96%, 90%, and 97.5%, respectively. These results demonstrate the effectiveness of the proposed SVM-based approach for tomato leaf disease detection.
format Article
id doaj-art-94e8d59293e34965ab223217cd1df034
institution DOAJ
issn 0126-0537
2477-8516
language English
publishDate 2025-05-01
publisher Universitas Brawijaya
record_format Article
series AGRIVITA Journal of Agricultural Science
spelling doaj-art-94e8d59293e34965ab223217cd1df0342025-08-20T03:21:55ZengUniversitas BrawijayaAGRIVITA Journal of Agricultural Science0126-05372477-85162025-05-0147233835310.17503/agrivita.v47i2.3746862Support Vector Machine (SVM) for Tomato Leaf Disease DetectionShafaf Ibrahim0Nur Afiqah Mohd Fuad1Nor Azura Md Ghani2Raihah Aminuddin3Budi Sunarko4School of Computing Sciences, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Shah Alam, MalaysiaSchool of Computing Sciences, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Melaka, MalaysiaSchool of Computing Sciences, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Shah Alam, MalaysiaSchool of Computing Sciences, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Melaka, MalaysiaDepartment of Electrical Engineering, Universitas Negeri Semarang, Semarang, Central Java, IndonesiaTomatoes rank among the top five most globally demanded crops and serve as a key ingredient in numerous dishes. However, productivity may decline due to challenges such as diseases, pest infestations, and climate change. Therefore, automatic disease detection is essential to identify early signs of illness during the growth period. This study proposes a method for detecting tomato leaf diseases using image processing techniques. The approach involves image enhancement, feature extraction, and classification. Initially, leaf disease images were enhanced using the Contrast Adjustment technique. Subsequently, color and texture features were extracted using Color Moments and the Gray-Level Co-occurrence Matrix (GLCM), respectively. Disease detection was carried out using a Support Vector Machine (SVM). The method was tested on 50 images each for healthy leaves and four types of tomato leaf diseases: Bacterial Spot, Yellow Leaf Curl Virus, Early Blight, and Late Blight. The performance of the disease detection system was evaluated using a confusion matrix, achieving an overall accuracy, sensitivity, and specificity of 96%, 90%, and 97.5%, respectively. These results demonstrate the effectiveness of the proposed SVM-based approach for tomato leaf disease detection.https://agrivita.ub.ac.id/index.php/agrivita/article/view/3746classificationdetectionfeature extractionleaf diseasesupport vector machine (svm)
spellingShingle Shafaf Ibrahim
Nur Afiqah Mohd Fuad
Nor Azura Md Ghani
Raihah Aminuddin
Budi Sunarko
Support Vector Machine (SVM) for Tomato Leaf Disease Detection
AGRIVITA Journal of Agricultural Science
classification
detection
feature extraction
leaf disease
support vector machine (svm)
title Support Vector Machine (SVM) for Tomato Leaf Disease Detection
title_full Support Vector Machine (SVM) for Tomato Leaf Disease Detection
title_fullStr Support Vector Machine (SVM) for Tomato Leaf Disease Detection
title_full_unstemmed Support Vector Machine (SVM) for Tomato Leaf Disease Detection
title_short Support Vector Machine (SVM) for Tomato Leaf Disease Detection
title_sort support vector machine svm for tomato leaf disease detection
topic classification
detection
feature extraction
leaf disease
support vector machine (svm)
url https://agrivita.ub.ac.id/index.php/agrivita/article/view/3746
work_keys_str_mv AT shafafibrahim supportvectormachinesvmfortomatoleafdiseasedetection
AT nurafiqahmohdfuad supportvectormachinesvmfortomatoleafdiseasedetection
AT norazuramdghani supportvectormachinesvmfortomatoleafdiseasedetection
AT raihahaminuddin supportvectormachinesvmfortomatoleafdiseasedetection
AT budisunarko supportvectormachinesvmfortomatoleafdiseasedetection