Cover Image

Evaluation of scratch and pre-trained convolutional neural networks for the classification of tomato plant diseases

Plant diseases are a major cause of destruction and death of most plants and especially trees. However, with the help of early detection, this issue can be solved and treated appropriately. A timely and accurate diagnosis is critical in maintaining the quality of crops. Recent innovations in the fie...

Full description

Saved in:
Bibliographic Details
Main Authors: Aquil, M.A.I., Ishak, W.H.W.
Format: Article
Published: Institute of Advanced Engineering and Science 2021
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107677569&doi=10.11591%2fIJAI.V10.I2.PP467-475&partnerID=40&md5=b00fe2d6f6d1e6bace0c3990f3ad7dd3
http://eprints.utp.edu.my/23750/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utp.eprints.23750
record_format eprints
spelling my.utp.eprints.237502021-08-19T10:01:55Z Evaluation of scratch and pre-trained convolutional neural networks for the classification of tomato plant diseases Aquil, M.A.I. Ishak, W.H.W. Plant diseases are a major cause of destruction and death of most plants and especially trees. However, with the help of early detection, this issue can be solved and treated appropriately. A timely and accurate diagnosis is critical in maintaining the quality of crops. Recent innovations in the field of deep learning (DL), especially in convolutional neural networks (CNNs) have achieved great breakthroughs across different applications such as the classification of plant diseases. This study aims to evaluate scratch and pre-trained CNNs in the classification of tomato plant diseases by comparing some of the state-of-the-art architectures including densely connected convolutional network (Densenet) 120, residual network (ResNet) 101, ResNet 50, ReseNet 30, ResNet 18, squeezenet and Vgg.net. The comparison was then evaluated using a multiclass statistical analysis based on the F-Score, specificity, sensitivity, precision, and accuracy. The dataset used for the experiments was drawn from 9 classes of tomato diseases and a healthy class from PlantVillage. The findings show that the pretrained Densenet-120 performed excellently with 99.68 precision, 99.84 F-1 score, and 99.81 accuracy, which is higher compared to its non-trained based model showing the effectiveness of using a combination of a CNN model with fine-tuning adjustment in classifying crop diseases. © 2021, Institute of Advanced Engineering and Science. All rights reserved. Institute of Advanced Engineering and Science 2021 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107677569&doi=10.11591%2fIJAI.V10.I2.PP467-475&partnerID=40&md5=b00fe2d6f6d1e6bace0c3990f3ad7dd3 Aquil, M.A.I. and Ishak, W.H.W. (2021) Evaluation of scratch and pre-trained convolutional neural networks for the classification of tomato plant diseases. IAES International Journal of Artificial Intelligence, 10 (2). pp. 467-475. http://eprints.utp.edu.my/23750/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description Plant diseases are a major cause of destruction and death of most plants and especially trees. However, with the help of early detection, this issue can be solved and treated appropriately. A timely and accurate diagnosis is critical in maintaining the quality of crops. Recent innovations in the field of deep learning (DL), especially in convolutional neural networks (CNNs) have achieved great breakthroughs across different applications such as the classification of plant diseases. This study aims to evaluate scratch and pre-trained CNNs in the classification of tomato plant diseases by comparing some of the state-of-the-art architectures including densely connected convolutional network (Densenet) 120, residual network (ResNet) 101, ResNet 50, ReseNet 30, ResNet 18, squeezenet and Vgg.net. The comparison was then evaluated using a multiclass statistical analysis based on the F-Score, specificity, sensitivity, precision, and accuracy. The dataset used for the experiments was drawn from 9 classes of tomato diseases and a healthy class from PlantVillage. The findings show that the pretrained Densenet-120 performed excellently with 99.68 precision, 99.84 F-1 score, and 99.81 accuracy, which is higher compared to its non-trained based model showing the effectiveness of using a combination of a CNN model with fine-tuning adjustment in classifying crop diseases. © 2021, Institute of Advanced Engineering and Science. All rights reserved.
format Article
author Aquil, M.A.I.
Ishak, W.H.W.
spellingShingle Aquil, M.A.I.
Ishak, W.H.W.
Evaluation of scratch and pre-trained convolutional neural networks for the classification of tomato plant diseases
author_facet Aquil, M.A.I.
Ishak, W.H.W.
author_sort Aquil, M.A.I.
title Evaluation of scratch and pre-trained convolutional neural networks for the classification of tomato plant diseases
title_short Evaluation of scratch and pre-trained convolutional neural networks for the classification of tomato plant diseases
title_full Evaluation of scratch and pre-trained convolutional neural networks for the classification of tomato plant diseases
title_fullStr Evaluation of scratch and pre-trained convolutional neural networks for the classification of tomato plant diseases
title_full_unstemmed Evaluation of scratch and pre-trained convolutional neural networks for the classification of tomato plant diseases
title_sort evaluation of scratch and pre-trained convolutional neural networks for the classification of tomato plant diseases
publisher Institute of Advanced Engineering and Science
publishDate 2021
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107677569&doi=10.11591%2fIJAI.V10.I2.PP467-475&partnerID=40&md5=b00fe2d6f6d1e6bace0c3990f3ad7dd3
http://eprints.utp.edu.my/23750/
_version_ 1738656516319215616
score 13.211869

Similar Items