Detection Method of Concave Defect on Specular Surfaces Based on Swin Transformer

Kazumoto Tanaka

doi:10.56741/IISTR.esl.00743

Authors

Kazumoto Tanaka
kazumoto@hiro.kindai.ac.jp
Kindai University https://orcid.org/0000-0002-7324-3201

Keywords:

automated surface inspection, concavity defect, optical simulation, optical specular surface, swin transformer

Abstract

Shallow concave defects on mirrored surfaces are difficult to detect automatically. This paper proposes a defect detection method using a deep neural network (DNN) that learns the presence or absence of distortion in the image of a stripe pattern reflected on a mirror surface. The Swin Transformer is used as the DNN to capture global features of the edges of the reflection. In the manufacturing process, the occurrence of defects is minimized, so it is difficult to collect enough defect images for training purposes. Therefore, in this paper, we show how to generate a large number of images of stripe pattern reflections using an optical simulation method. Our Swin Transformer showed high detection performance in defect detection experiments using actual mirrored parts.

Downloads

Download data is not yet available.

Author Biography

Kazumoto Tanaka, Kindai University

is with the Department of Informatics at Kindai University, Higashi-Hiroshima, Japan. He received his B.S. degree in Science in 1981 from Chiba University and his PhD from Tokushima University. His research interests focus on image processing and computer vision, with a particular emphasis on advancing the understanding and applications of these technologies. He has made significant contributions to the field of informatics, particularly in the areas of visual data analysis and computational techniques. (email: kazumoto@hiro.kindai.ac.jp).

References

V. Azamfirei, F. Psarommatis, and Y. Lagrosen, “Application of Automation for In-Line Quality Inspection, A Zero-Defect Manufacturing Approach,” Journal of Manufacturing Systems, 67, 1-22, 2023. https://doi.org/10.1016/j.jmsy.2022.12.010 DOI: https://doi.org/10.1016/j.jmsy.2022.12.010

A. Tjolleng, J. Chang, J. Park, W. Lee, M. Cha, J. Park, and K. Jung, “Development of A Human-friendly Visual Inspection Method for Painted Vehicle Bodies,” Applied Ergonomics, 106(103911), 2023. DOI: https://doi.org/10.1016/j.apergo.2022.103911

Y. Roh, S. Kim, H. Shim, D. Lim and D. Jeong, "A Patterned Illumination and Phase Integration Imaging Method for High-Glossy Surface Evaluation," proc. 2010 International Symposium on Optomechatronic Technologies, Toronto, Canada, 2010. doi: 10.1109/ISOT.2010.5687315 DOI: https://doi.org/10.1109/ISOT.2010.5687315

P. M. F. Forte, P. E. R. Felgueiras, F. P. Ferreira, M. A. Sousa, E. J. Nunes-Pereira, B. P. J. Bret, and M. S. Belsley, “Exploring Combined Dark and Bright Field Illumination to Improve the Detection of Defects on Specular Surfaces,” Optics and Lasers in Engineering, 88, 120-128, 2017. https://doi.org/10.1016/j.optlaseng.2016.08.002 DOI: https://doi.org/10.1016/j.optlaseng.2016.08.002

A.-C. Wei, Y-.C. Chang, and J.-R. Sze, “Study on Reduction of Background Fringes for Defect Detection of Specular Surface,” proc. 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, Taipei, Taiwan, 2023. doi: 10.1109/APSIPAASC58517.2023.10317452 DOI: https://doi.org/10.1109/APSIPAASC58517.2023.10317452

C. Zuo, S. Feng, L. Huang, T. Tao, W. Yin, and Q. Chen, “Phase Shifting Algorithms for Fringe Projection Profilometry: A review,” Optics and Lasers in Engineering, 109, 23-59, 2018. https://doi.org/10.1016/j.optlaseng.2018.04.019 DOI: https://doi.org/10.1016/j.optlaseng.2018.04.019

S. Ordones, M. Servin, M. Padilla, I. Choque, J. L. Flores, and A. Muñozc, “Shape Defect Measurement by Fringe Projection Profilometry and Phase-Shifting Algorithms,” Optical Engineering, 59(1), 014107, 2020. doi: 10.1117/1.OE.59.1.014107 DOI: https://doi.org/10.1117/1.OE.59.1.014107

M. C. Knauer, J. Kaminski, and G. Hausler, “Phase Measuring Deflectometry: A New Approach to Measure Specular Free-Form Surfaces,” proc. Optical Metrology in Production Engineering, Strasbourg, France, 2004. https://doi.org/10.1117/12.545704 DOI: https://doi.org/10.1117/12.545704

S. Bazeille, A. Meguenani, K. Tout, S. Kohler, O. Jrad, J.-P. Chambard and C. Cudel, “A Scanning Deflectometry Scheme for Online Defect Detection and 3-D Reconstruction of Specular Reflective Materials,” The International Journal of Advanced Manufacturing Technology, 131, 245–259, 2024. https://doi.org/10.1007/s00170-024-13034-8 DOI: https://doi.org/10.1007/s00170-024-13034-8

M. Song, J. Yi, S. Wei, and Z. Wen, "Mirror-like Defect Detection Technology based on YOLOv5 and Phase Measuring Deflectometry,” proc. 2nd International Conference on Robotics, Artificial Intelligence and Intelligent Control, Mianyang, China, 2023. 10.1109/RAIIC59453.2023.10280830. DOI: https://doi.org/10.1109/RAIIC59453.2023.10280830

J. Guan, J. Li, X. Yang, X. Chen, and J. Xi, “Defect Detection Method for Specular Surfaces based on Deflectometry and Deep Learning,” Optical Engineering, 61(6), 061407, 2022. https://doi.org/10.1117/1.OE.61.6.061407 DOI: https://doi.org/10.1117/1.OE.61.6.061407

J. Guan, J. Fei, W. Li, X. Jiang, L. Wub, Y. Liub, and J. Xi, “Defect Classification for Specular Surfaces based on Deflectometry and Multi-Modal Fusion Network,” Optics and Lasers in Engineering, 163(107488), 2023. https://doi.org/10.1016/j.optlaseng.2023.107488 DOI: https://doi.org/10.1016/j.optlaseng.2023.107488

X. Fang, Q. Luo, B. Zhou, C. Li, and L. Tian, “Research Progress of Automated Visual Surface Defect Detection for Industrial Metal Planar Materials,” Sensors, 20(18), 5136, 2020. https://doi.org/10.3390/s20185136 DOI: https://doi.org/10.3390/s20185136

Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo, “Swin Transformer: Hierarchical Vision Transformer using Shifted Windows,” Proc. ICCV2021, (virtual), Oct. 2021. doi:10.1109/ICCV48922.2021.00986 DOI: https://doi.org/10.1109/ICCV48922.2021.00986

A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. G., Ł. Kaiser, and I. Polosukhin, “Attention is All you Need,” Proc. NIPS 2017, Long Beach, USA, Dec. 2017.

A. Wang, M. Ren, and R. S. Zemel, “SketchEmbedNet: Learning Novel Concepts by Imitating Drawings,” Proc. ICML2021, (Virtual), 2021.

O. Hirose, A. Ishii, S. Hata and I. Washizaki, “Detection of Small Convex and Concave Defects on Optical Films by Patterned Illumination (2nd Report) - Estimation of Defect Detection by using Ray Tracing Method -,” Journal of the Japan Society of Precision Engineering, vol. 67, no. 7, pp. 1135-1139, 2001. DOI: https://doi.org/10.2493/jjspe.67.1135

A. S. Glassner (ed), An Introduction to Ray Tracing, Academic Press, New York, USA, 1989.

J. F. Blinn, "Models of Light Reflection for Computer Synthesized Pictures," in Proc. SIGGRAPH '77, California, USA, 1977. DOI: https://doi.org/10.1145/563858.563893

Z. Liu, H. Hu, Y. Lin, Z. Yao, Z. Xie, Y. Wei, J. Ning, Y. Cao, et al., "Swin Transformer V2: Scaling Up Capacity and Resolution," Proc. CVPR2022, New Orleans, USA, Jun. 2022. doi: 10.1109/CVPR52688.2022.01170 DOI: https://doi.org/10.1109/CVPR52688.2022.01170

D.P. Kingma and J. Ba, “Adam: A method for stochastic optimization, Proc. ICLR2015, San Diego, USA, May, 2015.