Abstract
Surface defect classification (SDC) is the visual inspection of the surface of an object to identify appearance defects. Efficient and accurate SDC is i mportant for improving the quality of industrial products. A manually designed convolutional neural network (CNN) is traditionally used for SDC. In this study, a simpler SDC scheme with a higher classification accuracy, named NAS-SDC, is developed based on the neural architecture search (NAS) technique. A max-pooling cell based on NASNet is introduced to reduce the search space and the number of network parameters, thus simplifying the candidate operators for the search. Two network architectures are proposed to stack the search candidates or the best cells. The proposed method can be used to automatically design an efficient CNN model for SDC on a specific dataset. Experimental results show that the proposed method can find the best cells in ~11 h using a single graphics processing unit (GPU) and achieves higher classification accuracies (99.98%, 99.8% and 99.26%) than state-of-the-art methods on the Northeastern University (NEU-CLS), DAGM, and bridge defect datasets. The number of network parameters used in the proposed method is only 0.35 M, and the average test time per sample is approximately 61 ms, thus achieving a balance between performance and speed.
Similar content being viewed by others
References
Baker B, Gupta O, Naik N, Raskar R (2016) Designing neural network architectures using reinforcement learning. arXiv preprint arXiv:1611.02167
Brock A, Lim T, Ritchie JM, Weston N (2017) SMASH: one-shot model architecture search through hypernetworks. arXiv preprint arXiv:1708.05344
Cai N, Lin J, Ye Q, Wang H, Weng S, Ling BWK (2017) A new IC solder joint inspection method for an automatic optical inspection system based on an improved visual background extraction algorithm. IEEE Trans Compon Packag Manuf Technol 6:161–172. https://doi.org/10.1109/TCPMT.2015.2501284
Chen PH, Ho SS (2016) Is overfeat useful for image-based surface defect classification tasks? In: 2016 IEEE international conference on image processing (ICIP). IEEE, Phoenix, AZ, pp 749–753
Chondronasios A, Popov I, Jordanov I (2016) Feature selection for surface defect classification of extruded aluminum profiles. Int J Adv Manuf Technol 83:33–41. https://doi.org/10.1007/s00170-015-7514-3
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, IEEE, Miami, FL, pp 248–255
Elsken T, Metzen JH, Hutter F (2018) Neural architecture search: a survey. arXiv preprint arXiv:1808.05377. https://doi.org/10.1007/978-3-030-05318-5_11
Gao H, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, Honolulu, HI, pp 4700–4708
Hassaballah M, Abdelmgeid AA, Hammam AA (2016) Image feature detectors and descriptors: foundations and applications, chapter image features detection, description and matching. Springer International Publishing, Cham
Hassaballah M, Awad AI (2020) Deep learning in computer vision: principles and applications. CRC Press, Boca Raton
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, Las Vegas, NV, pp 770–778
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861
Hsieh YA, Tsai YJ (2020) Machine learning for crack detection: review and model performance comparison. J Comput Civ Eng 34:04020038. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000918
Jager M, Knoll C, Hamprecht FA (2008) Weakly supervised learning of a classifier for unusual event detection. IEEE Trans Image Process 17:1700–1708. https://doi.org/10.1109/TIP.2008.2001043
Jiang X, Scott P, Whitehouse D (2008) Wavelets and their applications for surface metrology. CIRP Ann 57:555–558. https://doi.org/10.1016/j.cirp.2008.03.110
Lei J, Gao X, Feng Z, Qiu H, Song M (2018) Scale insensitive and focus driven mobile screen defect detection in industry. Neurocomputing 294:72–81. https://doi.org/10.1016/j.neucom.2018.03.013
Liang-Fu L, Wei-Fei M, Li L, Cheng L (2019) Research on detection algorithm for bridge cracks based on deep learning. Acta Automat Sin 45:1727–1742
Lin M, Chen Q, Yan S (2014) Network in network. CoRR abs/1312.4400
Liu H, Simonyan K, Yang Y (2018) Darts: differentiable architecture search. arXiv preprint arXiv:1806.09055
Pham H, Guan MY, Zoph B, Le QV, Dean J (2018) Efficient neural architecture search via parameter sharing. arXiv preprint arXiv:1802.03268
Real E, Aggarwal A, Huang Y, Le QV (2019) Regularized evolution for image classifier architecture search. Conf Artif Intell 33:4780–4789. https://doi.org/10.1609/aaai.v33i01.33014780
Ren R, Hung T, Tan KC (2018) A generic deep-learning-based approach for automated surface inspection. IEEE Trans Cybern 48:929–940. https://doi.org/10.1109/TCYB.2017.2668395
Shao Z, Wang L, Wang Z, Deng J (2019) Remote sensing image super-resolution using sparse representation and coupled sparse autoencoder. IEEE J Sel Top Appl Earth Obs Remote Sens 12:2663–2674. https://doi.org/10.1109/JSTARS.2019.2925456
Siebel NT, Sommer G (2008) Learning defect classifiers for visual inspection images by neuro-evolution using weakly labelled training data. In: 2008 IEEE congress on evolutionary computation (IEEE world congress on computational intelligence), IEEE, Hong Kong, pp 3925–3931
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Song K, Yan Y (2013) A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects. Appl Surf Sci 285:858–864. https://doi.org/10.1016/j.apsusc.2013.09.002
Stanley KO, Clune J, Lehman J, Miikkulainen R (2019) Designing neural networks through neuroevolution. Nature Mach Intell 1:24–35. https://doi.org/10.1038/s42256-018-0006-z
Sun L, Zhao C, Yan Z, Liu P, Duckett T, Stolkin R (2018) A novel weakly-supervised approach for RGB-D-based nuclear waste object detection. IEEE Sensors J 19:3487–3500. https://doi.org/10.1109/JSEN.2018.2888815
Tang Z, Yu H, Lu C, Liu P, Jin X (2019) Single-trial classification of different movements on one arm based on ERD/ERS and corticomuscular coherence. IEEE Access 7:128185–128197. https://doi.org/10.1109/ACCESS.2019.2940034
Timm F, Barth E (2011) Non-parametric texture defect detection using Weibull features. In: image processing: machine vision applications IV, International Society for Optics and Photonics, pp 78,770j
Wang T, Chen Y, Qiao M, Snoussi H (2018) A fast and robust convolutional neural network-based defect detection model in product quality control. Int J Adv Manuf Technol 94:3465–3471. https://doi.org/10.1007/s00170-017-0882-0
Wang P, Chen P, Yuan Y, Liu D, Huang Z, Hou X, Cottrell G (2018) Understanding convolution for semantic segmentation. In: 2018 IEEE winter conference on applications of computer vision (WACV), IEEE, Lake Tahoe, NV, pp 1451–1460
Weimer D, Scholz-Reiter B, Shpitalni M (2016) Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection. CIRP Ann 65:417–420. https://doi.org/10.1016/j.cirp.2016.04.072
Xian T, Wang Z, Zhang Z, Zhang D, Xu D, Gong X, Lei Z (2018) Wire defect recognition of spring-wire socket using multitask convolutional neural networks. IEEE Trans Compon Packag Manuf Technol 8:689–698. https://doi.org/10.1109/TCPMT.2018.2794540
Xiao M, Jiang M, Li G, Xie L, Yi L (2017) An evolutionary classifier for steel surface defects with small sample set. EURASIP J Image Video Process 2017:48. https://doi.org/10.1186/s13640-017-0197-y
Zhong Z, Yan J, Wu W, Shao J, Liu CL (2018) Practical block-wise neural network architecture generation. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR), IEEE, Salt Lake City, UT, pp 2423–2432
Zoph B, Le QV (2016) Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578
Zoph B, Vasudevan V, Shlens J, Le QV (2018) Learning transferable architectures for scalable image recognition. In: 2018 IEEE/CVF conference on computer vision and pattern recognition, IEEE, Salt Lake City, UT, pp 8697–8710
Acknowledgments
This research was supported in part by the National Natural Science Foundation of China (61941202), the Guangxi Natural Science Foundation (2018GXNSFBA281081), and the Guangxi Key Laboratory Fund of Embedded Technology and Intelligent System (2019-01-08, 2019-02-01).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yang, T., Zhang, T. & Huang, L. Classification of industrial surface defects based on neural architecture search. Multimed Tools Appl 80, 5187–5202 (2021). https://doi.org/10.1007/s11042-020-09968-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09968-2