Using image augmentation techniques and convolutional neural networks to identify insect infestations on tomatoes

Pest insects are a danger to both regional and global food security. In Jordan, the most productive crop is tomato. Jordan's agriculture output is threatened by insect infestations. The study intends to use a deep learning model called convolutional neural networks on a dataset that includes ei...

Full description

Saved in:
Bibliographic Details
Main Authors: Moy'awiah Al-Shannaq, Shahed N. Alkhateeb, Mohammad Wedyan
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Heliyon
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405844024175111
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850073850952286208
author Moy'awiah Al-Shannaq
Shahed N. Alkhateeb
Mohammad Wedyan
author_facet Moy'awiah Al-Shannaq
Shahed N. Alkhateeb
Mohammad Wedyan
author_sort Moy'awiah Al-Shannaq
collection DOAJ
description Pest insects are a danger to both regional and global food security. In Jordan, the most productive crop is tomato. Jordan's agriculture output is threatened by insect infestations. The study intends to use a deep learning model called convolutional neural networks on a dataset that includes eight categories of insect pest images. A dataset was used and a group of images from reliable sources were added to it. The image collection was analyzed, and an image augmentation technique was used to increase the number of images, which reached 5894 after image augmentation. The data was split among 80 % training and 20 % validation. Convolutional Neural Networks trained on the data achieved 90 % training accuracy, 85 % testing accuracy, and 87 % validation accuracy. A high-accuracy deep learning model was developed that may be utilized on mobile applications to detect pests that affected crops to assist farmers. The original database used was small in size. When tested on deep learning and machine learning systems, the accuracy was very low, reaching 50–60 % without image augmentation, despite image enhancement techniques.
format Article
id doaj-art-2fcb4597edbd4a648fee41aab83b8177
institution DOAJ
issn 2405-8440
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Heliyon
spelling doaj-art-2fcb4597edbd4a648fee41aab83b81772025-08-20T02:46:43ZengElsevierHeliyon2405-84402025-01-01111e4148010.1016/j.heliyon.2024.e41480Using image augmentation techniques and convolutional neural networks to identify insect infestations on tomatoesMoy'awiah Al-Shannaq0Shahed N. Alkhateeb1Mohammad Wedyan2Faculty of Information Technology and Computer Sciences, Yarmouk University, JordanFaculty of Information Technology and Computer Sciences, Yarmouk University, JordanCorresponding author.; Faculty of Information Technology and Computer Sciences, Yarmouk University, JordanPest insects are a danger to both regional and global food security. In Jordan, the most productive crop is tomato. Jordan's agriculture output is threatened by insect infestations. The study intends to use a deep learning model called convolutional neural networks on a dataset that includes eight categories of insect pest images. A dataset was used and a group of images from reliable sources were added to it. The image collection was analyzed, and an image augmentation technique was used to increase the number of images, which reached 5894 after image augmentation. The data was split among 80 % training and 20 % validation. Convolutional Neural Networks trained on the data achieved 90 % training accuracy, 85 % testing accuracy, and 87 % validation accuracy. A high-accuracy deep learning model was developed that may be utilized on mobile applications to detect pests that affected crops to assist farmers. The original database used was small in size. When tested on deep learning and machine learning systems, the accuracy was very low, reaching 50–60 % without image augmentation, despite image enhancement techniques.http://www.sciencedirect.com/science/article/pii/S2405844024175111AgricultureCrop diseaseNew technologiesAugmented realityDeep learningConvolutional neural networks
spellingShingle Moy'awiah Al-Shannaq
Shahed N. Alkhateeb
Mohammad Wedyan
Using image augmentation techniques and convolutional neural networks to identify insect infestations on tomatoes
Heliyon
Agriculture
Crop disease
New technologies
Augmented reality
Deep learning
Convolutional neural networks
title Using image augmentation techniques and convolutional neural networks to identify insect infestations on tomatoes
title_full Using image augmentation techniques and convolutional neural networks to identify insect infestations on tomatoes
title_fullStr Using image augmentation techniques and convolutional neural networks to identify insect infestations on tomatoes
title_full_unstemmed Using image augmentation techniques and convolutional neural networks to identify insect infestations on tomatoes
title_short Using image augmentation techniques and convolutional neural networks to identify insect infestations on tomatoes
title_sort using image augmentation techniques and convolutional neural networks to identify insect infestations on tomatoes
topic Agriculture
Crop disease
New technologies
Augmented reality
Deep learning
Convolutional neural networks
url http://www.sciencedirect.com/science/article/pii/S2405844024175111
work_keys_str_mv AT moyawiahalshannaq usingimageaugmentationtechniquesandconvolutionalneuralnetworkstoidentifyinsectinfestationsontomatoes
AT shahednalkhateeb usingimageaugmentationtechniquesandconvolutionalneuralnetworkstoidentifyinsectinfestationsontomatoes
AT mohammadwedyan usingimageaugmentationtechniquesandconvolutionalneuralnetworkstoidentifyinsectinfestationsontomatoes