Abstract
Defect inspection using computer vision is one of the most widespread artificial intelligence application. However, this technique has some serious limitations. Images from high reflective flat surfaces such as metal sheets may contain high amounts of glare, which makes them unsuitable for training, as defects may be hidden beneath disturbing reflections. Moreover, 3D defects may not be detected with conventional 2D camera. Finally, AI systems rely on large labelled image datasets for training, which may be extremely difficult and expensive to obtain. To solve these issues, in this paper we propose a procedure for detecting 2D and 3D defects on metal blanks based on an RGB camera, a laser light source and a limited defect dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alhwarin, F., Wang, C.C., Ristić-Durrant, D., Gräser, A.: Improved sift-features matching for object recognition. In: BCS International Academic Conference (2008)
Clark, J., Trucco, E., Wolff, L.B.: Using light polarization in laser scanning. Image Vis. Comput. 15(2), 107–117 (1997)
Jones, B.F., Fairney, P.: Recognition of shiny dielectric objects by analysing the polarization of reflected light. Image Vis. Comput. 7(4), 253–258 (1989)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates, Inc. (2012). http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
Luo, Q., Fang, X., Liu, L., Yang, C., Sun, Y.: Automated visual defect detection for flat steel surface: a survey. IEEE Trans. Instrum. Measure. 69, 626–644 (2020)
Natarajan, V., Hung, T.Y., Vaikundam, S., Chia, L.T.: Convolutional networks for voting-based anomaly classification in metal surface inspection. In: 2017 IEEE International Conference on Industrial Technology (ICIT), pp. 986–991 (2017)
Skiena, S.: Divide and Conquer, pp. 147–169 (2020)
Yun, J.P., Shin, W.C., Koo, G., Kim, M.S., Lee, C., Lee, S.J.: Automated defect inspection system for metal surfaces based on deep learning and data augmentation. J. Manuf. Syst. 55, 317–324 (2020). https://www.sciencedirect.com/science/article/pii/S027861252030042X
Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. Patt. Anal. Mach. Intell. 22(11), 1330–1334 (2000)
Acknowledgement
This material is based upon work supported by AEI-010500-2021b-143. Project ID: INSPECTOR - Investigación de tecnologías de percepción e inteligencia artificial para inspección on-line in cooperation with ArcelorMittal Tailored Blanks, ASAI and the Automotive Cluster of Aragon.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Monzón, L., Cantón, D., Sierra, F., Lázaro, M.T. (2023). Enhanced RGB Image Processing Method for Automatic 2D and 3D Defect Inspection on Shiny Surfaces. In: Tardioli, D., Matellán, V., Heredia, G., Silva, M.F., Marques, L. (eds) ROBOT2022: Fifth Iberian Robotics Conference. ROBOT 2022. Lecture Notes in Networks and Systems, vol 589. Springer, Cham. https://doi.org/10.1007/978-3-031-21065-5_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-21065-5_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21064-8
Online ISBN: 978-3-031-21065-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)