Enhancing Tomato Leaf Disease Detection via Optimized VGG16 and Transfer Learning Techniques

Identification of tomato leaf disease remains difficult because standard approaches are frequently incorrect in identifying distinct signs. Convolutional Neural Networks (CNNs) perform well in image classification and pattern identification, although they are prone to overfitting. Thus, max pooling...

Full description

Saved in:
Bibliographic Details
Main Authors: Sandy Putra Siregar, Imam Akbari, Poningsih Poningsih, Anjar Wanto, Solikhun Solikhun
Format: Article
Language:English
Published: Ikatan Ahli Informatika Indonesia 2025-06-01
Series:Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Subjects:
Online Access:https://jurnal.iaii.or.id/index.php/RESTI/article/view/6410
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849708043203248128
author Sandy Putra Siregar
Imam Akbari
Poningsih Poningsih
Anjar Wanto
Solikhun Solikhun
author_facet Sandy Putra Siregar
Imam Akbari
Poningsih Poningsih
Anjar Wanto
Solikhun Solikhun
author_sort Sandy Putra Siregar
collection DOAJ
description Identification of tomato leaf disease remains difficult because standard approaches are frequently incorrect in identifying distinct signs. Convolutional Neural Networks (CNNs) perform well in image classification and pattern identification, although they are prone to overfitting. Thus, max pooling was employed to reduce dimensionality while retaining crucial information. This paper offers an improved CNN through hyperparameter tuning and compares it to Transfer Learning models such as InceptionV3, NASNetMobile, and VGG16, which were chosen for their efficiency and accuracy. The dataset comprises 7,178 photos classified as Healthy, Leaf Late Blight, Septoria Leaf Spot, and Yellow Leaf Curl Virus, collected from Kaggle.. The dataset is separated into three sections: training, validation, and testing, with a ratio of 70:15:15. The results of this study revealed that the proposed method achieved the highest accuracy of 98.24%. In the application of transfer learning, the inceptionV3 model achieved an accuracy of 96.94%, whereas NASNetMobile obtained 97.50%, and VGG16 showed an accuracy of 96.76%. The evaluation is based on accuracy, precision, recall, F1-score and Inference time to determine the optimum model for accuracy and computing efficiency. This project uses the proposed method and Transfer Learning Techniques to categorize illness images on tomato leaves. These findings will drive further research to improve tehe performance of the proposed method for foliar disease classification and comparable applications.
format Article
id doaj-art-eec4006afa9947ec97e31beead8e26cf
institution DOAJ
issn 2580-0760
language English
publishDate 2025-06-01
publisher Ikatan Ahli Informatika Indonesia
record_format Article
series Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
spelling doaj-art-eec4006afa9947ec97e31beead8e26cf2025-08-20T03:15:47ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602025-06-019357058010.29207/resti.v9i3.64106410Enhancing Tomato Leaf Disease Detection via Optimized VGG16 and Transfer Learning TechniquesSandy Putra Siregar0Imam Akbari1Poningsih Poningsih2Anjar Wanto3Solikhun Solikhun4STIKOM Tunas Bangsa, Pematangsiantar, IndonesiaSTIKOM Tunas Bangsa, Pematangsiantar, IndonesiaSTIKOM Tunas Bangsa, Pematangsiantar, IndonesiaSTIKOM Tunas Bangsa, Pematangsiantar, IndonesiaSTIKOM Tunas Bangsa, Pematangsiantar, IndonesiaIdentification of tomato leaf disease remains difficult because standard approaches are frequently incorrect in identifying distinct signs. Convolutional Neural Networks (CNNs) perform well in image classification and pattern identification, although they are prone to overfitting. Thus, max pooling was employed to reduce dimensionality while retaining crucial information. This paper offers an improved CNN through hyperparameter tuning and compares it to Transfer Learning models such as InceptionV3, NASNetMobile, and VGG16, which were chosen for their efficiency and accuracy. The dataset comprises 7,178 photos classified as Healthy, Leaf Late Blight, Septoria Leaf Spot, and Yellow Leaf Curl Virus, collected from Kaggle.. The dataset is separated into three sections: training, validation, and testing, with a ratio of 70:15:15. The results of this study revealed that the proposed method achieved the highest accuracy of 98.24%. In the application of transfer learning, the inceptionV3 model achieved an accuracy of 96.94%, whereas NASNetMobile obtained 97.50%, and VGG16 showed an accuracy of 96.76%. The evaluation is based on accuracy, precision, recall, F1-score and Inference time to determine the optimum model for accuracy and computing efficiency. This project uses the proposed method and Transfer Learning Techniques to categorize illness images on tomato leaves. These findings will drive further research to improve tehe performance of the proposed method for foliar disease classification and comparable applications.https://jurnal.iaii.or.id/index.php/RESTI/article/view/6410leaf diseaseimagesclassificationproposed methodtransfer learning
spellingShingle Sandy Putra Siregar
Imam Akbari
Poningsih Poningsih
Anjar Wanto
Solikhun Solikhun
Enhancing Tomato Leaf Disease Detection via Optimized VGG16 and Transfer Learning Techniques
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
leaf disease
images
classification
proposed method
transfer learning
title Enhancing Tomato Leaf Disease Detection via Optimized VGG16 and Transfer Learning Techniques
title_full Enhancing Tomato Leaf Disease Detection via Optimized VGG16 and Transfer Learning Techniques
title_fullStr Enhancing Tomato Leaf Disease Detection via Optimized VGG16 and Transfer Learning Techniques
title_full_unstemmed Enhancing Tomato Leaf Disease Detection via Optimized VGG16 and Transfer Learning Techniques
title_short Enhancing Tomato Leaf Disease Detection via Optimized VGG16 and Transfer Learning Techniques
title_sort enhancing tomato leaf disease detection via optimized vgg16 and transfer learning techniques
topic leaf disease
images
classification
proposed method
transfer learning
url https://jurnal.iaii.or.id/index.php/RESTI/article/view/6410
work_keys_str_mv AT sandyputrasiregar enhancingtomatoleafdiseasedetectionviaoptimizedvgg16andtransferlearningtechniques
AT imamakbari enhancingtomatoleafdiseasedetectionviaoptimizedvgg16andtransferlearningtechniques
AT poningsihponingsih enhancingtomatoleafdiseasedetectionviaoptimizedvgg16andtransferlearningtechniques
AT anjarwanto enhancingtomatoleafdiseasedetectionviaoptimizedvgg16andtransferlearningtechniques
AT solikhunsolikhun enhancingtomatoleafdiseasedetectionviaoptimizedvgg16andtransferlearningtechniques