Transfer and unsupervised learning : an integrated approach to concrete crack image analysis

Gradišar, Luka (author), Dolenc, Matevž (author)

The detection of cracks in concrete structures is crucial for the assessment of their structural integrity and safety. To this end, detection with deep neural convolutional networks has been extensively researched in recent years. Despite their success, these methods are limited in classifying concrete as cracked or non-cracked and disregard other characteristics, such as the severity of the cracks. Furthermore, the classification process can be affected by various sources of interference and noise in the images. In this paper, an integrated methodology for analysing concrete crack images is proposed using transfer and unsupervised learning. The method extracts image features using pretrained networks and groups them based on similarity using hierarchical clustering. Three pre-trained networks are used for this purpose, with Inception v3 performing the best. The clustering results show the ability to divide images into different clusters based on image characteristics. In this way, various clusters are identified, such as clusters containing images of obstruction, background debris, edges, surface roughness, as well as cracked and uncracked concrete. In addition, dimensionality reduction is used to further separate and visualise the data, making it easier to analyse clustering results and identify misclassified images. This revealed several mislabelled images in the dataset used in this study. Additionally, a correlation was found between the principal components and the severity of cracks and surface imperfections. The results of this study demonstrate the potential of unsupervised learning for analysing concrete crack image data to distinguish between noisy images and the severity of cracks, which can provide valuable information for building more accurate predictive models.

• Language: English
• Keywords: clustering, crack detection, data mining, image analysis, transfer learning, unsupervised learning
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FGG - Faculty of Civil and Geodetic Engineering
• Publication status: Published
• Publication version: Version of Record
• Year: 2023
• Number of pages: 14 str.
• Numbering: Vol. 15, iss. 4, art. 3653
• PID: 20.500.12556/RUL-146416
• UDC: 004:69
• ISSN on article: 2071-1050
• DOI: 10.3390/su15043653
• COBISS.SI-ID: 142062083
• Publication date in RUL: 31.05.2023

Record is a part of a journal

• Title: Sustainability
• Shortened title: Sustainability
• Publisher: MDPI
• ISSN: 2071-1050
• COBISS.SI-ID: 5324897

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: gručenje, odkrivanje razpok, podatkovno rudarjenje, analiza slik, učenje s prenosom znanja, nenadzorovano učenje

Projects

• Funder: ARRS - Slovenian Research Agency
• Funding programme: Young researchers