DenseHillNet: a lightweight CNN for accurate classification of natural images

The detection of natural images, such as glaciers and mountains, holds practical applications in transportation automation and outdoor activities. Convolutional neural networks (CNNs) have been widely employed for image recognition and classification tasks. While previous studies have focused on fru...

Full description

Bibliographic Details
Published in:PeerJ Computer Science
Main Author: Saqib S.M.; Asghar M.Z.; Iqbal M.; Al-Rasheed A.; Khan M.A.; Ghadi Y.; Mazhar T.
Format: Article
Language:English
Published: PeerJ Inc. 2024
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85194107878&doi=10.7717%2fPEERJ-CS.1995&partnerID=40&md5=dc5ba4da33ef36ee83aa5ffc818534f4
id 2-s2.0-85194107878
spelling 2-s2.0-85194107878
Saqib S.M.; Asghar M.Z.; Iqbal M.; Al-Rasheed A.; Khan M.A.; Ghadi Y.; Mazhar T.
DenseHillNet: a lightweight CNN for accurate classification of natural images
2024
PeerJ Computer Science
10

10.7717/PEERJ-CS.1995
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85194107878&doi=10.7717%2fPEERJ-CS.1995&partnerID=40&md5=dc5ba4da33ef36ee83aa5ffc818534f4
The detection of natural images, such as glaciers and mountains, holds practical applications in transportation automation and outdoor activities. Convolutional neural networks (CNNs) have been widely employed for image recognition and classification tasks. While previous studies have focused on fruits, land sliding, and medical images, there is a need for further research on the detection of natural images, particularly glaciers and mountains. To address the limitations of traditional CNNs, such as vanishing gradients and the need for many layers, the proposed work introduces a novel model called DenseHillNet. The model utilizes a DenseHillNet architecture, a type of CNN with densely connected layers, to accurately classify images as glaciers or mountains. The model contributes to the development of automation technologies in transportation and outdoor activities. The dataset used in this study comprises 3,096 images of each of the ‘‘glacier’’ and ‘‘mountain’’ categories. Rigorous methodology was employed for dataset preparation and model training, ensuring the validity of the results. A comparison with a previous work revealed that the proposed DenseHillNet model, trained on both glacier and mountain images, achieved higher accuracy (86%) compared to a CNN model that only utilized glacier images (72%). Researchers and graduate students are the audience of our article. © 2024 Saqib et al. Distributed under Creative Commons CC-BY 4.0. All Rights Reserved.
PeerJ Inc.
23765992
English
Article
All Open Access; Gold Open Access
author Saqib S.M.; Asghar M.Z.; Iqbal M.; Al-Rasheed A.; Khan M.A.; Ghadi Y.; Mazhar T.
spellingShingle Saqib S.M.; Asghar M.Z.; Iqbal M.; Al-Rasheed A.; Khan M.A.; Ghadi Y.; Mazhar T.
DenseHillNet: a lightweight CNN for accurate classification of natural images
author_facet Saqib S.M.; Asghar M.Z.; Iqbal M.; Al-Rasheed A.; Khan M.A.; Ghadi Y.; Mazhar T.
author_sort Saqib S.M.; Asghar M.Z.; Iqbal M.; Al-Rasheed A.; Khan M.A.; Ghadi Y.; Mazhar T.
title DenseHillNet: a lightweight CNN for accurate classification of natural images
title_short DenseHillNet: a lightweight CNN for accurate classification of natural images
title_full DenseHillNet: a lightweight CNN for accurate classification of natural images
title_fullStr DenseHillNet: a lightweight CNN for accurate classification of natural images
title_full_unstemmed DenseHillNet: a lightweight CNN for accurate classification of natural images
title_sort DenseHillNet: a lightweight CNN for accurate classification of natural images
publishDate 2024
container_title PeerJ Computer Science
container_volume 10
container_issue
doi_str_mv 10.7717/PEERJ-CS.1995
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85194107878&doi=10.7717%2fPEERJ-CS.1995&partnerID=40&md5=dc5ba4da33ef36ee83aa5ffc818534f4
description The detection of natural images, such as glaciers and mountains, holds practical applications in transportation automation and outdoor activities. Convolutional neural networks (CNNs) have been widely employed for image recognition and classification tasks. While previous studies have focused on fruits, land sliding, and medical images, there is a need for further research on the detection of natural images, particularly glaciers and mountains. To address the limitations of traditional CNNs, such as vanishing gradients and the need for many layers, the proposed work introduces a novel model called DenseHillNet. The model utilizes a DenseHillNet architecture, a type of CNN with densely connected layers, to accurately classify images as glaciers or mountains. The model contributes to the development of automation technologies in transportation and outdoor activities. The dataset used in this study comprises 3,096 images of each of the ‘‘glacier’’ and ‘‘mountain’’ categories. Rigorous methodology was employed for dataset preparation and model training, ensuring the validity of the results. A comparison with a previous work revealed that the proposed DenseHillNet model, trained on both glacier and mountain images, achieved higher accuracy (86%) compared to a CNN model that only utilized glacier images (72%). Researchers and graduate students are the audience of our article. © 2024 Saqib et al. Distributed under Creative Commons CC-BY 4.0. All Rights Reserved.
publisher PeerJ Inc.
issn 23765992
language English
format Article
accesstype All Open Access; Gold Open Access
record_format scopus
collection Scopus
_version_ 1809678155294703616