Multi-class classification method using twin support vector machines with multi-information for steel surface defects
Authors:
- Maoxiang ChuMCMaoxiang Chu
- Xiaoping LiuXLXiaoping Liu
- Rongfen GongRGRongfen Gong
- Liming LiuLLLiming Liu
- 1 May 2018
- journal article
- research article
- Published by Elsevier in Chemometrics and Intelligent Laboratory Systems
- Vol. 176, 108-118
Abstract
No abstract availableKeywords
Funding Information
- Liaoning Province (201601291)
- Liaoning Province Ministry of Education (2017LNQN11, 2016TSPY13)
- Harbin Institute of Technology (SKLRS-2016-KF-08)
- University of Science and Technology Liaoning Foundation (2015RC06)
This publication has 27 references indexed in Scilit:
- A cost-effective and automatic surface defect inspection system for hot-rolled flat steelRobotics and Computer-Integrated Manufacturing, 2016
- A Fast Detection Method for Region of Defect on Strip Steel SurfaceISIJ International, 2015
- Weighted linear loss twin support vector machine for large-scale classificationKnowledge-Based Systems, 2015
- Sparse least square support vector machine via coupled compressive pruningNeurocomputing, 2014
- Multi-class Classification Methods of Enhanced LS-TWSVM for Strip Steel Surface DefectsJournal of Iron and Steel Research International, 2014
- Surface Defect Detection Method Using Saliency Linear Scanning Morphology for Silicon Steel Strip under Oil Pollution InterferenceISIJ International, 2014
- Support Vector Machine Classifier With Pinball LossIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- A local annular contrast based real-time inspection algorithm for steel bar surface defectsApplied Surface Science, 2012
- Sparse conjugate directions pursuit with application to fixed-size kernel modelsMachine Learning, 2011
- Watersheds in digital spaces: an efficient algorithm based on immersion simulationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991