Steel surface defect classification using multiple hyper-spheres support vector machine with additional information

Abstract A novel multiple hyper-spheres support vector machine with additional information (MHSVM+) is proposed for multi-class steel surface defects classification. Originated from binary twin hyper-spheres support vector machine, MHSVM+ uses hyper-sphere to solve classification decision problem. Differently, MHSVM+ is a multi-class classifier, where it builds a corresponding hyper-sphere for each type of defect dataset. Moreover, MHSVM+ introduces learning paradigm using additional information, which means it can learn additional information hidden in defect dataset. Two types of additional information are provided: local neighbor information and local density information. Local neighbor information contains local classification results for defect samples. And local density information is used to capture label noise, isolated samples and important samples in defect dataset. The above two types of additional information are introduced into MHSVM+ model. Finally, MHSVM+ classifier is used to classify six types of steel surface defects. Experimental results show that the novel multi-class classifier has perfect classification accuracy for defect dataset, especially corrupted defect dataset.

[1]  Anirban Mukherjee,et al.  Automatic Defect Detection on Hot-Rolled Flat Steel Products , 2013, IEEE Transactions on Instrumentation and Measurement.

[2]  Dong Xu,et al.  Bi-density twin support vector machines for pattern recognition , 2013, Neurocomputing.

[3]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[4]  Ridong Zhang,et al.  Prediction of human promoter with Least Square Support Vector Machine based on Kernel Locality Preserving Projection , 2016 .

[5]  Chih-Hsing Lin,et al.  Switching Bilateral Filter With a Texture/Noise Detector for Universal Noise Removal , 2010, IEEE Transactions on Image Processing.

[6]  G. Fu,et al.  Stable biomarker screening and classification by subsampling-based sparse regularization coupled with support vector machines in metabolomics , 2017 .

[7]  Amir Hossein Alavi,et al.  Detection of fatigue cracking in steel bridge girders: A support vector machine approach , 2017 .

[8]  Xiaoping Liu,et al.  The Strip Steel Surface Defect Recognition Based on Multiple Support Vector Hyper‐Sphere with Feature and Sample Weights , 2016 .

[9]  Yunhui Yan,et al.  Vision-based automatic detection of steel surface defects in the cold rolling process: considering the influence of industrial liquids and surface textures , 2017 .

[10]  Luc Vincent,et al.  Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Zhitong Yang,et al.  New watershed segmentation algorithm based on hybrid gradient and self-adaptive marker extraction , 2016, 2016 2nd IEEE International Conference on Computer and Communications (ICCC).

[12]  Mohammad Reza Yazdchi,et al.  Detection and Classification of Surface Defects of Cold Rolling Mill Steel Using Morphology and Neural Network , 2008, 2008 International Conference on Computational Intelligence for Modelling Control & Automation.

[13]  Mao-xiang Chu,et al.  Multi-class classification for steel surface defects based on machine learning with quantile hyper-spheres , 2017 .

[14]  Vladimir Vapnik,et al.  A new learning paradigm: Learning using privileged information , 2009, Neural Networks.

[15]  Shailender Gupta,et al.  An extension to switching bilateral filter for mixed noise removal from colour image , 2016 .

[16]  Johan A. K. Suykens,et al.  Support Vector Machine Classifier With Pinball Loss , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Franz Pernkopf,et al.  Detection of surface defects on raw steel blocks using Bayesian network classifiers , 2004, Pattern Analysis and Applications.

[18]  Maoxiang Chu,et al.  Multi-class Classification Methods of Enhanced LS-TWSVM for Strip Steel Surface Defects , 2014 .

[19]  Zheng Cao,et al.  Robust support vector machines based on the rescaled hinge loss function , 2017, Pattern Recognition.

[20]  Reshma Khemchandani,et al.  Twin Support Vector Machines for Pattern Classification , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Yuanxiang Li,et al.  Classification of defects in steel strip surface based on multiclass support vector machine , 2014, Multimedia Tools and Applications.

[22]  Liqiang Nie,et al.  Surface defect classification in large-scale strip steel image collection via hybrid chromosome genetic algorithm , 2016, Neurocomputing.

[23]  Maoxiang Chu,et al.  A Fast Detection Method for Region of Defect on Strip Steel Surface , 2015 .

[24]  Tianlong Zhang,et al.  Classification of steel samples by laser-induced breakdown spectroscopy and random forest , 2016 .

[25]  Marco Vannucci,et al.  A fuzzy inference system applied to defect detection in flat steel production , 2010, International Conference on Fuzzy Systems.

[26]  Robert P. W. Duin,et al.  Support Vector Data Description , 2004, Machine Learning.

[27]  Andreas K. Maier,et al.  Cryo-Balloon Catheter Localization Based on a Support-Vector-Machine Approach , 2016, IEEE Transactions on Medical Imaging.

[28]  Feng Xuehui,et al.  The Strip Steel Surface Defects Classification Method Based on Weak Classifier Adaptive Enhancement , 2011, 2011 Third International Conference on Measuring Technology and Mechatronics Automation.

[29]  Youping Chen,et al.  Classification of surface defects on steel sheet using convolutional neural networks , 2017 .

[30]  Z. Zhang,et al.  Online Surface Defects Detection System for Cold-rolled Steel Strip , 2017 .

[31]  Howard Huang,et al.  Process knowledge based multi-class support vector classification (PK-MSVM) approach for surface defects in hot rolling , 2011, Expert Syst. Appl..

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

[33]  Yi Lu Murphey,et al.  An intelligent real-time vision system for surface defect detection , 2004, ICPR 2004.

[34]  Fang Deng,et al.  Sensor Multifault Diagnosis With Improved Support Vector Machines , 2017, IEEE Transactions on Automation Science and Engineering.

[35]  Cheng Soon Ong,et al.  Learning SVM in Kreĭn Spaces , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Maoxiang Chu,et al.  Strip Steel Surface Defect Classification Method Based on Enhanced Twin Support Vector Machine , 2014 .

[37]  Dong Xu,et al.  A twin-hypersphere support vector machine classifier and the fast learning algorithm , 2013, Inf. Sci..