Abstract
The surface quality of steel plates that have been widely used in the manufacturing industry directly affects the final product performance. The existing inspection system of steel-plate surface defects has some drawbacks: (1) an unbalance problem in the steel-plate surface defect dataset, and (2) the number of classifiers used in the recognition process is insufficient for identifying stains, dirtiness, and other non-common defects. It is imperative to develop a new method to identify steel-plate surface defects. In this paper, the normalization technique and the synthetic minority over-sampling technique (SMOTE) are used to establish a steel-plate surface defect dataset with complete categories, balanced quantities, and normalized features. Based on the existing boosting algorithms in the literature, a new backward AdaBoost (AdaBoost.BK) algorithm is proposed for defect recognition. AdaBoost.BK selects the most suitable weak classifier by the filtering mechanism, thus increasing the number of weak classifiers that can be combined. Experiments show that the model not only improves the recognition accuracy of non-common defects, but also improves the accuracy of the whole classification.
Similar content being viewed by others
References
Tao F, Cheng J, Cheng Y, Gu S, Zheng T, Yang H (2017) SDMSim: a manufacturing service supply-demand matching simulator under cloud environment. Robot Comput Integr Manuf 45:34–46
Xiang F, Jiang G, Xu L, Wang N (2016) The case-library method for service composition and optimal selection of big manufacturing data in cloud manufacturing system. Int J Adv Manuf Technol 84(1–4):59–70
Sharifzadeh M, Alirezaee S, Amirfattahi R, Sadri S (2008) Detection of steel defect using the image processing algorithms. In: Multitopic Conference, 2008. INMIC 2008. IEEE International, IEEE, pp 125–127
Xiang F, Hu Y, Yu Y, Wu H (2014) QoS and energy consumption aware service composition and optimal-selection based on Pareto group leader algorithm in cloud manufacturing system. CEJOR 22(4):663–685
Neogi N, Mohanta DK, Dutta PK (2014) Review of vision-based steel surface inspection systems. EURASIP J Image Video Process 2014(1):50
Suresh BR, Fundakowski RA, Levitt TS, Overland JE (1983) A real-time automated visual inspection system for hot steel slabs. IEEE Trans Pattern Anal Mach Intell 6:563–572
Choi K, Koo K, Lee JS (2006) Development of defect classification algorithm for POSCO rolling strip surface inspection system. In: SICE-ICASE, 2006. International Joint Conference, IEEE, pp 2499–2502
Wu G, Zhang H, Sun X, Xu J, Xu K (2007) A bran-new feature extraction method and its application to surface defect recognition of hot rolled strips. In: Automation and Logistics, 2007 I.E. International Conference on, IEEE, pp 2069–2074
Dupont F, Odet C, Cartont M (1997) Optimization of the recognition of defects in flat steel products with the cost matrices theory. NDT E Int 30(1):3–10
Jia H, Murphey YL, Shi J, Chang TS (2004) An intelligent real-time vision system for surface defect detection. In: Pattern recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on IEEE, vol 3, pp 239–242
Ghorai S, Mukherjee A, Gangadaran M, Dutta PK (2013) Automatic defect detection on hot-rolled flat steel products. IEEE Trans Instrum Meas 62(3):612–621
Du W, Zhan Z (2002) Building decision tree classifier on private data. In: proceedings of the IEEE international conference on privacy, security and data mining-vol 14. Australian Computer Society, Inc, pp 1–8
Sahami M, Dumais S, Heckerman D, Horvitz E (1998) A Bayesian approach to filtering junk e-mail. In Learning for text categorization: papers from the 1998 workshop, vol 62, pp 98–105
Liu W, Liu H, Tao D, Wang Y, Lu K (2016) Manifold regularized kernel logistic regression for web image annotation. Neurocomputing 172:3–8
Yazdchi MR, Mahyari AG, Nazeri A (2008) Detection and classification of surface defects of cold rolling mill steel using morphology and neural network. In: Computational intelligence for modelling control & automation, 2008 international conference on, IEEE, pp 1071–1076
Peng K, Zhang X (2009) Classification technology for automatic surface defects detection of steel strip based on improved BP algorithm. In: Natural computation, 2009. ICNC'09. Fifth international conference on, IEEE, vol 1, pp 110–114
Liu YC, Hsu YL, Sun YN, Tsai SJ, Ho, CY, Chen CM (2010) A computer vision system for automatic steel surface inspection. In: Industrial electronics and applications (ICIEA), 2010 the 5th IEEE conference on, IEEE, pp 1667–1670
Valiant LG (1984) A theory of the learnable. Commun ACM 27(11):1134–1142
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357
Freund Y, Schapire RE (1995) A decision-theoretic generalization of on-line learning and an application to boosting. In: European conference on computational learning theory, Springer Berlin Heidelberg, pp 23–37
Wu X, Kumar V, Quinlan JR, Ghosh J, Yang Q, Motoda H, Zhou ZH (2008) Top 10 algorithms in data mining. Knowl Inf Syst 14(1):1–37
Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In: icml, vol. 96, pp 148–156
Schapire RE, Singer Y (1998) Improved boosting algorithms using confidence-rated predictions. In: Proceedings of the eleventh annual conference on Computational learning theory, ACM, pp 80–91
Zou H, Rosset S, Hastie T (2009) Multi-class AdaBoost. Statistics and its Interface, 2(3):349–360
Zhou M, Kong L, Xie L, Fu T, Jiang G, Feng Q (2017) Design and optimization of non-circular mortar nozzles using finite volume method and Taguchi method. Int J Adv Manuf Technol 90(9–12):3543–3553
Tao F, Guo H, Zhang L, Cheng Y (2012) Modelling of combinable relationship-based composition service network and the theoretical proof of its scale-free characteristics. Enterp Inf Syst 6(4):373–404
Tao F, Zhao D, Hu Y, Zhou Z (2008) Resource service composition and its optimal-selection based on particle swarm optimization in manufacturing grid system. IEEE Trans Ind Inf 4(4):315–327
Zhang Q, Sun S (2009) Weighted data normalization based on eigenvalues for artificial neural network classification. In: Neural information processing, Springer Berlin/Heidelberg, pp 349–356
Li N, Cheng X, Zhang S, Wu Z (2013) Recognizing human actions by BP-AdaBoost algorithm under a hierarchical recognition framework. In: Acoustics, speech and signal processing (ICASSP), 2013 I.E. international conference on, IEEE, pp 3407–3411
Uhrig RE (1995) Introduction to artificial neural networks. In: Industrial electronics, control, and instrumentation, proceedings of the 1995 I.E. IECON 21st International Conference on, IEEE, vol. 1, pp 33–37
Acknowledgements
This study was supported by the National Natural Science Foundation of China (NSFC) (Project No.51505350) and Teaching Research Project of Hubei Province (Project No.2013236 and 2014237) in China.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hu, L., Zhou, M., Xiang, F. et al. Modeling and recognition of steel-plate surface defects based on a new backward boosting algorithm. Int J Adv Manuf Technol 94, 4317–4328 (2018). https://doi.org/10.1007/s00170-017-1113-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-017-1113-4