Open AccessOn-machine surface defect detection using light scattering and deep learning
Author(s) -
Mingyu Li,
Chi Fai Cheung,
Nicola Senin,
Shixiang Wang,
Rong Su,
Richard Leach
Publication year - 2020
Publication title -
journal of the optical society of america. a, optics, image science, and vision./journal of the optical society of america. a, online
Language(s) - English
Resource type - Journals
eISSN - 1520-8532
pISSN - 1084-7529
DOI - 10.1364/josaa.394102
Subject(s) - scattering , light scattering , deep learning , convolutional neural network , surface (topology) , artificial intelligence , optics , computer science , artificial neural network , materials science , homogeneous , physics , mathematics , geometry , thermodynamics
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 microstructured surfaces produced by ultraprecision diamond machining.