Abstract
In order to accurately identify the defects on the aluminum surface, including perforation, stains, yellow spots and scratches, etc., a method combining the robust principal component analysis and the convolution neural network is proposed to detect defects on the surface of aluminum foil products. Firstly, the defect area image of aluminum foil was segmented by using the method of robust principal component analysis; Then, using TensorFlow platform to build CNN network model, loading aluminum foil images for training, and save the network model parameters of training results, on the basis of this network model, loading aluminum foil images acquired in real time and classify them, complete defect detection tasks. Experimental results showed that the proposed algorithm has the following advantages such as high accuracy, favorable expansibility and so on, it can be easily applied into surface defect detection for other objects.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sun, Bao-hua, Yue-ping Han, Qing Xu, et al. 2014. Product surface defect detection based on surf algorithm research. Infrared Technology 36 (6): 503–507.
Wang, Hui, and Hong Sun. 2017. Robust principal component analysis for aluminum foil surface defects detection. Journal of Signal Processing 33 (4): 577–582.
Yang, B., and L. Zou. 2015. Robust foreground detection using block-based RPCA. Optik—International Journal for Light and Electron Optics 126 (23): 4586–4590.
Yao, Ming-Hai, Jie Li, and Xian-Bao Wang. 2013. Solar cells surface defects detection using RPCA method. Chinese Journal of Computers 36 (9): 1943–1952.
Wang, P., Q. Chen, W. Qian, et al. 2017. Salient motion detection using proximal robust principal component analysis method. Journal of Electronic Imaging 26 (2): 023004.
Liu, X., Z. Liu, C. Li, et al. 2018. Fabric defect detection based on faster R-CNN. In Ninth international conference on graphic and image processing, 91–97.
Xu, Y., G. Yu, Y. Wang, et al. 2017. Car detection from low-altitude UAV imagery with the faster R-CNN. Journal of Advanced Transportation 2017: 1–10.
Li, S., Z.Q. Liu, and A.B. Chan. 2015. Heterogeneous multi-task learning for human pose estimation with deep convolutional neural network. International Journal of Computer Vision 113 (1): 19–36.
Philipp, K., P. Michael, and U. Martin. 2017. Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization. PeerJ 5: e3874.
Wright, J., A. Ganesh, S. Rao, et al. 2009. Robust principal component analysis: Exact recovery of corrupted low-rank matrices via convex optimization. In Proceedings of the conference on neural information processing systems, 2080–2088, Vancouver, Canada.
Elad, M., and A.M. Bruckstein. 2002. A generalized uncertainty principle and sparse representation in pairs of bases. IEEE Transactions on Information Theory 48 (9): 2558–2567.
Acknowledgements
The research is supported by the fund project of Guangxi young teachers basic ability enhancement project (2017KY0651), the fund project of Guilin University of Electronic Technology 2017 Key Laboratory of Cognitive Radio and Information Processing, Ministry of Education, 2018JGA284, 2016ZZSK15, 1608027, 201711838095, 201811838187.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, H., Gao, C., Wang, P. (2020). Aluminum Foil Surface Defect Recognition Method Based on CNN. In: Huang, C., Chan, YW., Yen, N. (eds) Data Processing Techniques and Applications for Cyber-Physical Systems (DPTA 2019). Advances in Intelligent Systems and Computing, vol 1088. Springer, Singapore. https://doi.org/10.1007/978-981-15-1468-5_28
Download citation
DOI: https://doi.org/10.1007/978-981-15-1468-5_28
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1467-8
Online ISBN: 978-981-15-1468-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)