Classification of defects in wooden structures using pre-trained models of convolutional neural network

<p>Wooden structures, over time, are challenged by different types of defects. Due to mechanical and weathering effects, these defects can occur in the form of cracks, live and dead knots, dampness, and others. Because of the risk of damage or complete failure, treatment of these defects is ne...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Rana Ehtisham (17820980) (author)
مؤلفون آخرون: Waqas Qayyum (17820983) (author), Charles V. Camp (17820986) (author), Vagelis Plevris (14158863) (author), Junaid Mir (17820989) (author), Qaiser-uz Zaman Khan (17820992) (author), Afaq Ahmad (5153747) (author)
منشور في: 2023
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513529500925952
author Rana Ehtisham (17820980)
author2 Waqas Qayyum (17820983)
Charles V. Camp (17820986)
Vagelis Plevris (14158863)
Junaid Mir (17820989)
Qaiser-uz Zaman Khan (17820992)
Afaq Ahmad (5153747)
author2_role author
author
author
author
author
author
author_facet Rana Ehtisham (17820980)
Waqas Qayyum (17820983)
Charles V. Camp (17820986)
Vagelis Plevris (14158863)
Junaid Mir (17820989)
Qaiser-uz Zaman Khan (17820992)
Afaq Ahmad (5153747)
author_role author
dc.creator.none.fl_str_mv Rana Ehtisham (17820980)
Waqas Qayyum (17820983)
Charles V. Camp (17820986)
Vagelis Plevris (14158863)
Junaid Mir (17820989)
Qaiser-uz Zaman Khan (17820992)
Afaq Ahmad (5153747)
dc.date.none.fl_str_mv 2023-12-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.cscm.2023.e02530
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Classification_of_defects_in_wooden_structures_using_pre-trained_models_of_convolutional_neural_network/25036391
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Civil engineering
Materials engineering
Information and computing sciences
Computer vision and multimedia computation
Machine learning
Wooden defects
Defects Classification
Pre-trained Models
CNN
dc.title.none.fl_str_mv Classification of defects in wooden structures using pre-trained models of convolutional neural network
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Wooden structures, over time, are challenged by different types of defects. Due to mechanical and weathering effects, these defects can occur in the form of cracks, live and dead knots, dampness, and others. Because of the risk of damage or complete failure, treatment of these defects is necessary, but doing so necessitates their proper identification and classification (categorization). Crack identification and categorization must be part of the inspection procedure for engineering structures in the built environment. Convolutional neural networks (CNNs), a sub-type of Deep Learning (DL), can automatically classify the images of wooden structures to identify such defects. In this study, ten pre-trained models of CNN, namely ResNet18, ResNet50, ResNet101, ShuffleNet, GoogLeNet, Inception-V3, MobileNet-V2, Xception, Inception-ResNet-V2, and NASNet-Mobile are evaluated for the tasks of classification and prediction of defects in wooden structures. Each pre-trained CNN model is additionally trained and validated on an image dataset of 9000 images, equally divided into three classes: cracks, knots, and intact (undamaged). A smaller dataset of 300 images is separately used for testing purposes. Statistical parameters such as accuracy, precision, recall, and F1-score are computed for each CNN model. The Inception-V3 model proved to be the best CNN model for classifying defects in wooden structures based on the model’s accuracy, processing time and overall performance.</p><h2>Other Information</h2> <p> Published in: Case Studies in Construction Materials<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.cscm.2023.e02530" target="_blank">https://dx.doi.org/10.1016/j.cscm.2023.e02530</a></p>
eu_rights_str_mv openAccess
id Manara2_289e0dca1d6b5fde6a0a6c4738615356
identifier_str_mv 10.1016/j.cscm.2023.e02530
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25036391
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Classification of defects in wooden structures using pre-trained models of convolutional neural networkRana Ehtisham (17820980)Waqas Qayyum (17820983)Charles V. Camp (17820986)Vagelis Plevris (14158863)Junaid Mir (17820989)Qaiser-uz Zaman Khan (17820992)Afaq Ahmad (5153747)EngineeringCivil engineeringMaterials engineeringInformation and computing sciencesComputer vision and multimedia computationMachine learningWooden defectsDefects ClassificationPre-trained ModelsCNN<p>Wooden structures, over time, are challenged by different types of defects. Due to mechanical and weathering effects, these defects can occur in the form of cracks, live and dead knots, dampness, and others. Because of the risk of damage or complete failure, treatment of these defects is necessary, but doing so necessitates their proper identification and classification (categorization). Crack identification and categorization must be part of the inspection procedure for engineering structures in the built environment. Convolutional neural networks (CNNs), a sub-type of Deep Learning (DL), can automatically classify the images of wooden structures to identify such defects. In this study, ten pre-trained models of CNN, namely ResNet18, ResNet50, ResNet101, ShuffleNet, GoogLeNet, Inception-V3, MobileNet-V2, Xception, Inception-ResNet-V2, and NASNet-Mobile are evaluated for the tasks of classification and prediction of defects in wooden structures. Each pre-trained CNN model is additionally trained and validated on an image dataset of 9000 images, equally divided into three classes: cracks, knots, and intact (undamaged). A smaller dataset of 300 images is separately used for testing purposes. Statistical parameters such as accuracy, precision, recall, and F1-score are computed for each CNN model. The Inception-V3 model proved to be the best CNN model for classifying defects in wooden structures based on the model’s accuracy, processing time and overall performance.</p><h2>Other Information</h2> <p> Published in: Case Studies in Construction Materials<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.cscm.2023.e02530" target="_blank">https://dx.doi.org/10.1016/j.cscm.2023.e02530</a></p>2023-12-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.cscm.2023.e02530https://figshare.com/articles/journal_contribution/Classification_of_defects_in_wooden_structures_using_pre-trained_models_of_convolutional_neural_network/25036391CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/250363912023-12-01T00:00:00Z
spellingShingle Classification of defects in wooden structures using pre-trained models of convolutional neural network
Rana Ehtisham (17820980)
Engineering
Civil engineering
Materials engineering
Information and computing sciences
Computer vision and multimedia computation
Machine learning
Wooden defects
Defects Classification
Pre-trained Models
CNN
status_str publishedVersion
title Classification of defects in wooden structures using pre-trained models of convolutional neural network
title_full Classification of defects in wooden structures using pre-trained models of convolutional neural network
title_fullStr Classification of defects in wooden structures using pre-trained models of convolutional neural network
title_full_unstemmed Classification of defects in wooden structures using pre-trained models of convolutional neural network
title_short Classification of defects in wooden structures using pre-trained models of convolutional neural network
title_sort Classification of defects in wooden structures using pre-trained models of convolutional neural network
topic Engineering
Civil engineering
Materials engineering
Information and computing sciences
Computer vision and multimedia computation
Machine learning
Wooden defects
Defects Classification
Pre-trained Models
CNN