For Libraries For Publication Open Access Downloads About Us Contact Us
Paper Titles
Testing Study on Ratio of Crack Widths on Two Sides of Protective Covering of Steel-Lined Reinforced Concrete Penstock
p.317
Characterizations of Plating Structures and Electromagnetic Shielding Properties of the Micron-Sized Flaky Silver-Coated Copper Powder
p.321
Study on Job Shop Scheduling Optimization with Multi-Objective
p.326
Investigation on Mixed Mode Stress Intensity Factors for Inclined Surface Crack in Finite-Thickness Plates and Parameters Influence
p.330
Image Classification for Steel Strip Surface Defects Based on Support Vector Machines
p.336
Study on the Application of Viscoelastic Material in Sound Absorption Structure Model
p.341
Study on Integrated Properties of PP Composites Filled with Rice Husks Powder
p.347
Numerical Simulation Technology for a Full Cycle of Steel Line Pipe Manufacturing Operations
p.353
Distribution of the Molecule Weight and Grain Size of Medium Temperature Phenol Formaldehyde Resin
p.359

Image Classification for Steel Strip Surface Defects Based on Support Vector Machines

Article Preview

Abstract:

In order to realize less time consuming and on-line image classification for steel strip surface defects, an improved multiclass support vector machine (SVM) was proposed. The SVM used a novel algorithm and only constructed (k-1) two-class SVMs where K is the number of classes. In the testing phase, to identify the surface defects it used a new unidirectional acyclic graph which had internal (k-1) nodes and k leaves. Its testing time is less than traditional multiclass SVM method. The experiment results shows that this method is simple and less time consuming while preserving generalization ability and recognition accuracy toward steel strip surface defects.

You might also be interested in these eBooks
High Performance Structures and Materials Engineering View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 217-218)

Pages:

336-340

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.217-218.336

Citation:

Cite this paper

Online since:

March 2011

Authors:

Yong Wei Yu, Guo Fu Yin, Liu Qing Du

Keywords:

Image Classification, Steel Strip, Support Vector Machine (SVM), Surface Defect

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2011 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

References

[1] Cortes C, Vapnik V: Machine Learning Vol. 20 (1995), p.273.

Google Scholar

[2] V. Vapnik: The Nature of Statistical Learning Theory (Springer, New York, 1995).

Google Scholar

[3] Smola AJ, Scholkopf B: Statistics and Computing Vol. 14 (2004), p.199.

Google Scholar

[4] Tipping ME; Journal of Machine Learning Research Vol. 1 (2001), p.211.

Google Scholar

[5] Mathias M. Adankon, Mohamed Cheriet: Pattern Recognition Vol. 42 (2009), p.3264.

Google Scholar

[6] Hwei Jen Lin, Jih Pin Yeh: Applied Mathematics and Computation Vol. 214 (2009), p.329.

Google Scholar

[7] Shinya Katagiri, Shigeo Abe: Pattern Recognition Letters Vol. 27 (2006), p.1495.

Google Scholar

[8] J.D. B Nelson, R.I. Damper, S.R. Gunn and B. GUO: Neurocomputing Vol. 72 (2008), p.15.

Google Scholar

[9] Ming-Huwi Horng: Expert Systems with Applications Vol. 36 (2009), p.8124.

Google Scholar

[10] Sumeet Agarwal, V. Vijaya Saradhi, Harish Karnick: Neurocomputing Vol. 71 (2008), p.1230.

DOI: 10.1016/j.neucom.2007.11.023

Google Scholar

[11] Yiguang Liu, Zhisheng and Liping Cao: Pattern Recognition Vol. 39 (2006), p.2258.

Google Scholar

[12] Chih-Wei Hsu and Chih-Jen Lin; IEEE Transaction on Neural Networks Vol. 13 (2002), p.415.

DOI: 10.1109/72.991427

Google Scholar

© 2025 Trans Tech Publications Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies. For open access content, terms of the Creative Commons licensing CC-BY are applied.
Scientific.Net is a registered trademark of Trans Tech Publications Ltd.