On-machine surface defect detection using light scattering and deep learning

Liu, Mingyu; Fai Cheung, Chi; Senin, Nicola; Wang, Shixiang; Su, Rong; Leach, Richard

Abstract

This paper presents an on-machine surface defect detection system using light scattering and deep learning. A supervised deep learning model is used to mine the information related to defects from light scattering patterns. A convolutional neural network is trained on a large dataset of scattering patterns that are predicted by a rigorous forward scattering model. The model is valid for any surface topography with homogeneous materials and has been verified by comparing with experimental data. Once the neural network is trained, it allows for fast, accurate and robust defect detection. The system capability is validated on micro-structured surfaces produced by ultra-precision diamond machining.

Citation

Liu, M., Fai Cheung, C., Senin, N., Wang, S., Su, R., & Leach, R. (2020). On-machine surface defect detection using light scattering and deep learning. Journal of the Optical Society of America A, 37(9), B53-B59. https://doi.org/10.1364/josaa.394102

• Journal Article Type: Article
• Acceptance Date: Jun 16, 2020
• Online Publication Date: Jul 24, 2020
• Publication Date: Sep 1, 2020
• Deposit Date: Jun 22, 2020
• Publicly Available Date: Jul 25, 2021
• Journal: Journal of the Optical Society of America A
• Print ISSN: 1084-7529
• Electronic ISSN: 1520-8532
• Publisher: Optical Society of America
• Peer Reviewed: Peer Reviewed
• Volume: 37
• Issue: 9
• Pages: B53-B59
• DOI: https://doi.org/10.1364/josaa.394102
• Keywords: Computer Vision and Pattern Recognition; Atomic and Molecular Physics, and Optics; Electronic, Optical and Magnetic Materials
• Public URL: https://nottingham-repository.worktribe.com/output/4702164
• Publisher URL: https://www.osapublishing.org/josaa/abstract.cfm?uri=josaa-37-9-B53
• Additional Information: This article is maintained by: OSA - The Optical Society; Crossref DOI link to publisher maintained version: https://doi.org/10.1364/JOSAA.394102; Article type: research-article; Similarity check: Screened by Similarity Check; Peer reviewed: Yes; Review process: Single blind; Received: 1 April 2020; Accepted: 16 June 2020; Published: 24 July 2020; Copyright: Published by The Optical Society under the terms of the Creative Commons Attribution 4.0 License. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.