
The Library
Wall crack multiclass classification : expertise-based dataset construction and learning algorithms performance comparison
Tools
Wibowo, Andi Prasetiyo, Adha, Augusta, Kurniawan, Ibnu F. and Laory, Irwanda (2022) Wall crack multiclass classification : expertise-based dataset construction and learning algorithms performance comparison. Buildings, 12 (12). 2135. doi:10.3390/buildings12122135 ISSN 2075-5309.
|
PDF
buildings-12-02135.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution 4.0. Download (6Mb) | Preview |
Official URL: http://doi.org/10.3390/buildings12122135
Abstract
Wall crack detection is one of the primary tasks in determining the structural integrity of a building for both restorative and preventive attempts. Machine learning techniques, such as deep learning (DL) with computer vision capabilities, have gradually become more prevalent as they can provide expert assessments with an acceptable performance when the crack detection involves a considerable number of structures. Despite such a prospective application, classification on different types of wall cracks is relatively less common, possibly due to the absence of the professional-standard-to-dataset translation. In this work, we utilised a complete pipeline, starting from novel dataset construction, ground truth formulation based on civil engineering standards, and training and testing steps. Our work focused on multi-class classification with regard to the binary classification (i.e., determining only two categories) used in previous studies. We implemented transfer learning based on VGG16 and RestNET50 for feature extraction, combined them with an ANN and kNN for the classifier, and compared their prediction performances. Our results indicate that the developed models can distinguish images that contain wall cracks into three categories of features based on the degree of damage: light, medium, and severe. Furthermore, since greyscale images offer more precise readings and predictions, the use of augmentation in dataset generation is critical. Although ResNet50 is the most stable network in terms of accuracy, it performs better when paired with kNN.
Item Type: | Journal Article | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software T Technology > TA Engineering (General). Civil engineering (General) T Technology > TH Building construction |
||||||||||||
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > Engineering | ||||||||||||
Library of Congress Subject Headings (LCSH): | Fracture mechanics , Fracture mechanics -- Data processing, Fracture mechanics -- Mathematical models, Walls, Structural engineering , Building failures, Neural networks (Computer science) , Transfer learning (Machine learning) | ||||||||||||
Journal or Publication Title: | Buildings | ||||||||||||
Publisher: | MDPI | ||||||||||||
ISSN: | 2075-5309 | ||||||||||||
Official Date: | 5 December 2022 | ||||||||||||
Dates: |
|
||||||||||||
Volume: | 12 | ||||||||||||
Number: | 12 | ||||||||||||
Article Number: | 2135 | ||||||||||||
DOI: | 10.3390/buildings12122135 | ||||||||||||
Status: | Peer Reviewed | ||||||||||||
Publication Status: | Published | ||||||||||||
Access rights to Published version: | Open Access (Creative Commons) | ||||||||||||
Date of first compliant deposit: | 1 March 2023 | ||||||||||||
Date of first compliant Open Access: | 1 March 2023 | ||||||||||||
RIOXX Funder/Project Grant: |
|
Request changes or add full text files to a record
Repository staff actions (login required)
![]() |
View Item |
Downloads
Downloads per month over past year