Manara - Qatar Research Repository
Browse
10.1016_j.cscm.2023.e02530.pdf (9.54 MB)

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

Download (9.54 MB)
journal contribution
submitted on 2024-01-21, 08:58 and posted on 2024-01-21, 10:36 authored by Rana Ehtisham, Waqas Qayyum, Charles V. Camp, Vagelis Plevris, Junaid Mir, Qaiser-uz Zaman Khan, Afaq Ahmad

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.

Other Information

Published in: Case Studies in Construction Materials
License: http://creativecommons.org/licenses/by/4.0/
See article on publisher's website: https://dx.doi.org/10.1016/j.cscm.2023.e02530

Funding

Open Access funding provided by the Qatar National Library.

History

Language

  • English

Publisher

Elsevier

Publication Year

  • 2023

License statement

This Item is licensed under the Creative Commons Attribution 4.0 International License.

Institution affiliated with

  • Qatar University
  • College of Engineering - QU