TY - JOUR
T1 - On-machine Surface Defect Detection Using Light Scattering and Deep Learning
AU - LIU, Mingyu
AU - Cheung, Chi Fai
AU - Senin, Nicola
AU - Wang, Shixiang
AU - So, Rong
AU - Leach, Richard
N1 - Funding Information:
Funding. Engineering and Physical Sciences Research Council (EP/R028826/1); European Union’s Horizon 2020 Research and Innovation Staff Exchange Programme (734174); Research Grants Council of the Government of the Hong Kong Special Administrative Region (15202717).
Funding Information:
Acknowledgment. We acknowledge the support from the Engineering and Physical Sciences Research Council, European Union’s Horizon 2020 Research and Innovation Staff Exchange Programme, Research Grants Council of the Government of the Hong Kong Special Administrative Region, China, and the access to the University of Nottingham’s Augusta HPC service.
Publisher Copyright:
© 2020 Optical Society of America
PY - 2020/9
Y1 - 2020/9
N2 - 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.
AB - 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.
UR - https://www.osapublishing.org/josaa/abstract.cfm?uri=josaa-37-9-B53
UR - http://www.scopus.com/inward/record.url?scp=85090348981&partnerID=8YFLogxK
U2 - 10.1364/JOSAA.394102
DO - 10.1364/JOSAA.394102
M3 - Journal article
SN - 1084-7529
VL - 37
SP - B53-B59
JO - Journal of the Optical Society of America A: Optics and Image Science, and Vision
JF - Journal of the Optical Society of America A: Optics and Image Science, and Vision
IS - 9
ER -