Vision-based detection of steel billet surface defects via fusion of multiple image features

Chao Yung Hsu; Li Wei Kang; Chih Yang Lin; Chia Hung Yeh; Chia Tsung Lin

doi:10.3233/978-1-61499-484-8-1239

Vision-based detection of steel billet surface defects via fusion of multiple image features

Chao Yung Hsu, Li Wei Kang, Chih Yang Lin, Chia Hung Yeh, Chia Tsung Lin

Department of Mechanical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Automatic inspection techniques have been widely employed to achieve high productivity while ensuring high-quality products in steel making industry. In this paper, a vision-based detection framework for automatically detecting different types of steel billet surface defects is proposed. The defects considered in this study includes cratches, corner cracks, sponge cracks, slivers, and roll marks. In the proposed framework, to improve the quality of image acquisition for billet surface, two preprocessing techniques, i.e., automatic identification of ROI (region of interest) and HDR (high dynamic range)-based image enhancement techniques, are proposed. Then, DWT (discrete wavelet transform)-based image feature is extracted from the image to be detected and fused with the other two extracted local features based on variance and illumination to identify each defect on the billet surface. Experimental results have verified the feasibility of the proposed method.

Original language	English
Title of host publication	Intelligent Systems and Applications - Proceedings of the International Computer Symposium, ICS 2014
Editors	William Cheng-Chung Chu, Han-Chieh Chao, Stephen Jenn-Hwa Yang
Publisher	IOS Press BV
Pages	1239-1247
Number of pages	9
ISBN (Electronic)	9781614994831
DOIs	https://doi.org/10.3233/978-1-61499-484-8-1239
State	Published - 2015
Event	International Computer Symposium, ICS 2014 - Taichung, Taiwan Duration: 12 Dec 2014 → 14 Dec 2014

Publication series

Name	Frontiers in Artificial Intelligence and Applications
Volume	274
ISSN (Print)	0922-6389
ISSN (Electronic)	1879-8314

Conference

Conference	International Computer Symposium, ICS 2014
Country/Territory	Taiwan
City	Taichung
Period	12/12/14 → 14/12/14

Keywords

defect detection
discrete wavelet transform
feature fusion
high dynamic range
region of interest
steel billet

Access to Document

10.3233/978-1-61499-484-8-1239

Cite this

Hsu, C. Y., Kang, L. W., Lin, C. Y., Yeh, C. H., & Lin, C. T. (2015). Vision-based detection of steel billet surface defects via fusion of multiple image features. In W. C.-C. Chu, H.-C. Chao, & S. J.-H. Yang (Eds.), Intelligent Systems and Applications - Proceedings of the International Computer Symposium, ICS 2014 (pp. 1239-1247). (Frontiers in Artificial Intelligence and Applications; Vol. 274). IOS Press BV. https://doi.org/10.3233/978-1-61499-484-8-1239

Hsu, Chao Yung ; Kang, Li Wei ; Lin, Chih Yang et al. / Vision-based detection of steel billet surface defects via fusion of multiple image features. Intelligent Systems and Applications - Proceedings of the International Computer Symposium, ICS 2014. editor / William Cheng-Chung Chu ; Han-Chieh Chao ; Stephen Jenn-Hwa Yang. IOS Press BV, 2015. pp. 1239-1247 (Frontiers in Artificial Intelligence and Applications).

@inproceedings{0d2102019c6142ee896ca88984f71d08,

title = "Vision-based detection of steel billet surface defects via fusion of multiple image features",

abstract = "Automatic inspection techniques have been widely employed to achieve high productivity while ensuring high-quality products in steel making industry. In this paper, a vision-based detection framework for automatically detecting different types of steel billet surface defects is proposed. The defects considered in this study includes cratches, corner cracks, sponge cracks, slivers, and roll marks. In the proposed framework, to improve the quality of image acquisition for billet surface, two preprocessing techniques, i.e., automatic identification of ROI (region of interest) and HDR (high dynamic range)-based image enhancement techniques, are proposed. Then, DWT (discrete wavelet transform)-based image feature is extracted from the image to be detected and fused with the other two extracted local features based on variance and illumination to identify each defect on the billet surface. Experimental results have verified the feasibility of the proposed method.",

keywords = "defect detection, discrete wavelet transform, feature fusion, high dynamic range, region of interest, steel billet",

author = "Hsu, {Chao Yung} and Kang, {Li Wei} and Lin, {Chih Yang} and Yeh, {Chia Hung} and Lin, {Chia Tsung}",

year = "2015",

doi = "10.3233/978-1-61499-484-8-1239",

language = "???core.languages.en_GB???",

series = "Frontiers in Artificial Intelligence and Applications",

publisher = "IOS Press BV",

pages = "1239--1247",

editor = "Chu, {William Cheng-Chung} and Han-Chieh Chao and Yang, {Stephen Jenn-Hwa}",

booktitle = "Intelligent Systems and Applications - Proceedings of the International Computer Symposium, ICS 2014",

}

Hsu, CY, Kang, LW, Lin, CY, Yeh, CH & Lin, CT 2015, Vision-based detection of steel billet surface defects via fusion of multiple image features. in WC-C Chu, H-C Chao & SJ-H Yang (eds), Intelligent Systems and Applications - Proceedings of the International Computer Symposium, ICS 2014. Frontiers in Artificial Intelligence and Applications, vol. 274, IOS Press BV, pp. 1239-1247, International Computer Symposium, ICS 2014, Taichung, Taiwan, 12/12/14. https://doi.org/10.3233/978-1-61499-484-8-1239

Vision-based detection of steel billet surface defects via fusion of multiple image features. / Hsu, Chao Yung; Kang, Li Wei; Lin, Chih Yang et al.
Intelligent Systems and Applications - Proceedings of the International Computer Symposium, ICS 2014. ed. / William Cheng-Chung Chu; Han-Chieh Chao; Stephen Jenn-Hwa Yang. IOS Press BV, 2015. p. 1239-1247 (Frontiers in Artificial Intelligence and Applications; Vol. 274).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Vision-based detection of steel billet surface defects via fusion of multiple image features

AU - Hsu, Chao Yung

AU - Kang, Li Wei

AU - Lin, Chih Yang

AU - Yeh, Chia Hung

AU - Lin, Chia Tsung

PY - 2015

Y1 - 2015

N2 - Automatic inspection techniques have been widely employed to achieve high productivity while ensuring high-quality products in steel making industry. In this paper, a vision-based detection framework for automatically detecting different types of steel billet surface defects is proposed. The defects considered in this study includes cratches, corner cracks, sponge cracks, slivers, and roll marks. In the proposed framework, to improve the quality of image acquisition for billet surface, two preprocessing techniques, i.e., automatic identification of ROI (region of interest) and HDR (high dynamic range)-based image enhancement techniques, are proposed. Then, DWT (discrete wavelet transform)-based image feature is extracted from the image to be detected and fused with the other two extracted local features based on variance and illumination to identify each defect on the billet surface. Experimental results have verified the feasibility of the proposed method.

AB - Automatic inspection techniques have been widely employed to achieve high productivity while ensuring high-quality products in steel making industry. In this paper, a vision-based detection framework for automatically detecting different types of steel billet surface defects is proposed. The defects considered in this study includes cratches, corner cracks, sponge cracks, slivers, and roll marks. In the proposed framework, to improve the quality of image acquisition for billet surface, two preprocessing techniques, i.e., automatic identification of ROI (region of interest) and HDR (high dynamic range)-based image enhancement techniques, are proposed. Then, DWT (discrete wavelet transform)-based image feature is extracted from the image to be detected and fused with the other two extracted local features based on variance and illumination to identify each defect on the billet surface. Experimental results have verified the feasibility of the proposed method.

KW - defect detection

KW - discrete wavelet transform

KW - feature fusion

KW - high dynamic range

KW - region of interest

KW - steel billet

UR - http://www.scopus.com/inward/record.url?scp=84926505737&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-484-8-1239

DO - 10.3233/978-1-61499-484-8-1239

M3 - 會議論文篇章

AN - SCOPUS:84926505737

T3 - Frontiers in Artificial Intelligence and Applications

SP - 1239

EP - 1247

BT - Intelligent Systems and Applications - Proceedings of the International Computer Symposium, ICS 2014

A2 - Chu, William Cheng-Chung

A2 - Chao, Han-Chieh

A2 - Yang, Stephen Jenn-Hwa

PB - IOS Press BV

T2 - International Computer Symposium, ICS 2014

Y2 - 12 December 2014 through 14 December 2014

ER -

Hsu CY, Kang LW, Lin CY, Yeh CH, Lin CT. Vision-based detection of steel billet surface defects via fusion of multiple image features. In Chu WCC, Chao HC, Yang SJH, editors, Intelligent Systems and Applications - Proceedings of the International Computer Symposium, ICS 2014. IOS Press BV. 2015. p. 1239-1247. (Frontiers in Artificial Intelligence and Applications). doi: 10.3233/978-1-61499-484-8-1239

Vision-based detection of steel billet surface defects via fusion of multiple image features

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this