A semi-supervised convolutional neural network-based method for steel surface defect recognition

Abstract Automatic defect recognition is one of the research hotspots in steel production, but most of the current methods focus on supervised learning, which relies on large-scale labeled samples. In some real-world cases, it is difficult to collect and label enough samples for model training, and this might impede the application of most current works. The semi-supervised learning, using both labeled and unlabeled samples for model training, can overcome this problem well. In this paper, a semi-supervised learning method using the convolutional neural network (CNN) is proposed for steel surface defect recognition. The proposed method requires fewer labeled samples, and the unlabeled data can be used to help training. And, the CNN is improved by Pseudo-Label. The experimental results on a benchmark dataset of steel surface defect recognition indicate that the proposed method can achieve good performances with limited labeled data, which achieves an accuracy of 90.7% with 17.53% improvement. Furthermore, the proposed method has been applied to a real-world case from a Chinese steel company, and obtains an accuracy of 86.72% which significantly better than the original method in this workshop.

[1]  Bernd Scholz-Reiter,et al.  Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection , 2016 .

[2]  Jürgen Schmidhuber,et al.  Steel defect classification with Max-Pooling Convolutional Neural Networks , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[3]  Diego Carou,et al.  Residual stresses evaluation in precision milling of hardened steel based on the deflection-electrochemical etching technique , 2017 .

[4]  Nicolas Le Roux,et al.  Efficient Non-Parametric Function Induction in Semi-Supervised Learning , 2004, AISTATS.

[5]  Blaine A. Price,et al.  Remote electronic examinations: student experiences , 2002, Br. J. Educ. Technol..

[6]  Sanjib Sinha,et al.  Clinical, electrophysiological, imaging, and ultrastructural description in 68 patients with neuronal ceroid lipofuscinoses and its subtypes. , 2014, Pediatric neurology.

[7]  Jean Ponce,et al.  A Theoretical Analysis of Feature Pooling in Visual Recognition , 2010, ICML.

[8]  P. Caleb,et al.  Classification of surface defects on hot rolled steel using adaptive learning methods , 2000, KES'2000. Fourth International Conference on Knowledge-Based Intelligent Engineering Systems and Allied Technologies. Proceedings (Cat. No.00TH8516).

[9]  Bokyoung Kang,et al.  Integrating independent component analysis and local outlier factor for plant-wide process monitoring , 2011 .

[10]  M. Matuszewski,et al.  Using artificial intelligence models for the prediction of surface wear based on surface isotropy levels , 2018, Robotics and Computer-Integrated Manufacturing.

[11]  Bin Sheng,et al.  Deep Convolutional Neural Networks for Human Action Recognition Using Depth Maps and Postures , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[12]  Shiji Song,et al.  Laplacian twin extreme learning machine for semi-supervised classification , 2018, Neurocomputing.

[13]  Pascal Vincent,et al.  Contractive Auto-Encoders: Explicit Invariance During Feature Extraction , 2011, ICML.

[14]  Yuxin Peng,et al.  SSDH: Semi-Supervised Deep Hashing for Large Scale Image Retrieval , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[15]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[16]  Dongrui Wu,et al.  Improved Neural Signal Classification in a Rapid Serial Visual Presentation Task Using Active Learning , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[17]  Liang Gao,et al.  A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method , 2018, IEEE Transactions on Industrial Electronics.

[18]  Liang Gao,et al.  A New Deep Transfer Learning Based on Sparse Auto-Encoder for Fault Diagnosis , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[19]  Wen Chen,et al.  A New Ensemble Approach based on Deep Convolutional Neural Networks for Steel Surface Defect classification , 2018 .

[20]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[21]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[22]  Wei Wu,et al.  Safety-aware Graph-based Semi-Supervised Learning , 2018, Expert Syst. Appl..

[23]  Gaël Varoquaux,et al.  The NumPy Array: A Structure for Efficient Numerical Computation , 2011, Computing in Science & Engineering.

[24]  Vitor Santos,et al.  Object recognition and pose estimation for industrial applications: A cascade system , 2014 .

[25]  Florent Dupont,et al.  Optimization of the recognition of defects in flat steel products with the cost matrices theory , 1997 .

[26]  Jian Yang,et al.  Convolution Neural Networks With Two Pathways for Image Style Recognition , 2017, IEEE Transactions on Image Processing.

[27]  Oliver Kramer,et al.  Fast and simple gradient-based optimization for semi-supervised support vector machines , 2014, Neurocomputing.

[28]  Stephen T. Newman,et al.  Influence of cutting environments on surface integrity and power consumption of austenitic stainless steel , 2015 .

[29]  Sang Woo Kim,et al.  Defect detection for corner cracks in steel billets using a wavelet reconstruction method. , 2014, Journal of the Optical Society of America. A, Optics, image science, and vision.

[30]  Yigang He,et al.  A cost-effective and automatic surface defect inspection system for hot-rolled flat steel , 2016 .

[31]  Yoshua Bengio,et al.  Challenges in representation learning: A report on three machine learning contests , 2013, Neural Networks.

[32]  Yunhui Yan,et al.  A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects , 2013 .

[33]  Kay Chen Tan,et al.  A Generic Deep-Learning-Based Approach for Automated Surface Inspection , 2018, IEEE Transactions on Cybernetics.

[34]  Jianzhu Wang,et al.  Online Rail Surface Inspection Utilizing Spatial Consistency and Continuity , 2020, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[35]  Sung Wook Baik,et al.  Efficient Deep CNN-Based Fire Detection and Localization in Video Surveillance Applications , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[36]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[37]  Zibin Zheng,et al.  Wide and Deep Convolutional Neural Networks for Electricity-Theft Detection to Secure Smart Grids , 2018, IEEE Transactions on Industrial Informatics.

[38]  Tapani Raiko,et al.  Semi-supervised Learning with Ladder Networks , 2015, NIPS.