A comparison of deep learning techniques for corrosion detection

Bolton, T ORCID: https://orcid.org/0000-0003-1599-8400, Bass, J ORCID: https://orcid.org/0000-0002-0570-7086 and Gaber, T ORCID: https://orcid.org/0000-0003-4065-4191 2022, A comparison of deep learning techniques for corrosion detection , in: Advanced Intelligent Systems and Informatics 2022. (In Press)

[img] PDF - Accepted Version
Restricted to Repository staff only

Download (674kB) | Request a copy

Abstract

Corrosion - degradation in metal structures - is problematic, expensive to rectify, and can be unpredictable in the rate at which it spreads. Traditional preventative maintenance techniques are complemented by human visual inspection, in turn complemented by artificial intelligence vision techniques. The primary objective of this paper was to determine the most accurate deep learning model for use in corrosion detection; to achieve this, we devised an experimental comparison that tested five machine learning algorithms for the detection of corrosion from image data. The deep learning that forms the basis of algorithms used to solve object recognition problems traditionally requires large amounts of training data. As this data requires manual labelling by a person who is expert in the domain of corrosion, it is difficult and expensive to obtain; time and expense that increase considerably as more sophisticated pixel-level annotation is applied. We discovered that high levels of accuracy (98%) can be achieved using deep learning to detect corrosion using samples annotated with simple, image-level labels. We achieved this headline accuracy through the application of transfer learning using models that had been trained on the ImageNet dataset. With many deep learning algorithms to choose from, we systematically determined the most accurate model to use as a basis for further experimentation.

Item Type: Conference or Workshop Item (Paper)
Schools: Schools > School of Computing, Science and Engineering
Funders: Add Energy Ltd., University of Salford
Depositing User: Thomas Bolton
Date Deposited: 22 Aug 2022 12:31
Last Modified: 22 Aug 2022 12:31
URI: http://usir.salford.ac.uk/id/eprint/64157

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)

Downloads

Downloads per month over past year