Application of Fractal Dimension Feature to Recognition of Surface Defects on Hot-Rolled Strips

Ke Xu; Peng Zhou; Chao Lin Yang

doi:10.4028/www.scientific.net/AMM.152-154.526

Paper Titles

Rapid Growth and Magnetic Properties of Fe₇CO₃ Intermetallic Compound
p.501

Determination of Cl^- and SO₄^2- in Boric Acid
p.507

Nanocrystalline Silicon Films with High Conductivity Prepared by Hot Wire Chemical Vapor Deposition
p.513

Effect of Templates on the Electrochromic Properties of Tungsten Oxide Thin Films
p.519

Application of Fractal Dimension Feature to Recognition of Surface Defects on Hot-Rolled Strips
p.526

Cooling System CAE Analysis and Optimization Design of Hot Stamping for High Strength Steel Sheet
p.531

Influence of Composition on the Corrosion of Steel Bar of Reinforced Geopolymer Concrete
p.536

The Research on the Dynamic Characteristic of Rubber Isolator
p.542

Environmental Effect on Fatigue Properties of Die-Cast Magnesium Alloys
p.548

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 152-154Application of Fractal Dimension Feature to...

Application of Fractal Dimension Feature to Recognition of Surface Defects on Hot-Rolled Strips

Abstract:

Because steel strips are covered with scales and water during hot-rolling, it is difficult to recognize the defects from images of hot-rolled strips through conventional methods. Principles and characteristics of fractal dimensions were studied, and computation of the fractal dimensions of the defect images with Peleg Covered Carpet is presented. Fractal dimensions of piecewise linearly transformed and smoothed images were used as features for classification of defects. These features were inputted to train the AdaBoost classifier. Experiments with samples of pimples, shells and scales from a real surface inspection system of hot-rolled strips showed that it is effective to recognized scales from other defects, and the total classification rate of this method is higher than 90%.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 152-154)

Pages:

526-530

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.152-154.526

Citation:

Cite this paper

Online since:

January 2012

Authors:

Ke Xu, Peng Zhou, Chao Lin Yang

Keywords:

Fractal Dimension, Hot-Rolled Strip, Surface Inspection

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Song Qiang, Xu Ke, and Xu Jinwu, Recognition of surface defects on medium and heavy plates based on structure spectrum, J. of university of science and technology Beijing, Beijing, 2007, Vol. 29, No. 3, pp.342-345.

Google Scholar

[2] Keller J, Chen S, and Crownover R, On the calculation of fractal features from images [J], IEEE Trans, PAMI, 1993, Vol. 15, No. 10, pp.1087-1090.

DOI: 10.1109/34.254066

Google Scholar

[3] Li qingzhong, and Wang Maohua, A fast identification for fruit fast defect based on fractal characters, Journal of image and graphics, Beijing, 2000, Vol. 5, No. 2, pp.144-148.

Google Scholar

[4] Dong Yuan, and Hu Guangrui, Technology of counting image fractal dimension, Computer Applications and software, Shanghai, 2007, Vol. 18, No. 6, pp.61-65.

Google Scholar

[5] PELEG. S, NAROLAND. J, HARTLEY.R. Multiple resolution texture analysis and classification[J]. IEEE Trans. PAMI, 1984, 6(4): 518-523.

DOI: 10.1109/tpami.1984.4767557

Google Scholar