The Visual Quality Recognition of Nonwovens Using a Novel Wavelet Based Contourlet Transform

Jian Li Liu; Bao Qi Zuo

doi:10.4028/www.scientific.net/AMR.267.884

Paper Titles

Vehicle Access Intelligent Monitoring and Network Management System Based on RFID Technology
p.862

A Visual-Thermal Image Sequence Registration Method Based on Motion Status Statistic Feature Multi-Resolution Analysis
p.867

An Image Mosaic Algorithm Taking into Account Speed and Robustness
p.873

Design of an E-Learning Based on Service Software Bus
p.879

The Visual Quality Recognition of Nonwovens Using a Novel Wavelet Based Contourlet Transform
p.884

Study and Implementation of the Vehicle Control Instruments
p.890

Design and Realization of Excellent Course Release Platform Based on Template Engines Technology
p.895

ZPD Incidence Development Strategy for Demand of Internet in Business-Teaching of CRHEIs
p.900

Object Manipulation Control Strategy Analysis Center of Humanoid Robot
p.904

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 267The Visual Quality Recognition of Nonwovens Using...

The Visual Quality Recognition of Nonwovens Using a Novel Wavelet Based Contourlet Transform

Abstract:

In this paper, a novel wavelet based contourlet transform for texture extraction is presented. In the texture analysis section, we propose a novel wavelet based contourlet transform, which can be considered as a simplified but more sufficient for texture analysis for nonwoven image compared with version of the one introduced by Eslami in theory view. In experiment, nonwoven images of five different visual quality grades, 125 of each grade, are decomposed using wavelet based contourlet transform with ‘PKVA’ filter as the default filter of Laplacian Pyramid (LP) and Directional Filter Bank (DFB) at 3 levels and two energy-based features, norm-1 L1 and norm-2 L2, are calculated from the wavelet coefficients at the first level and contourlet coefficients of each high frequency subband at different levels and directions to train and test SVM. When the nonwoven images are decomposed at 3 levels and 16 L1s are extracted, with 500 samples to train the SVM, the average recognition accuracy of test set is 98.4%, which is superior to the comparative method using wavelet texture analysis.

You might also be interested in these eBooks

Manufacturing Systems and Industry Application

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 267)

Pages:

884-889

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.267.884

Citation:

Cite this paper

Online since:

June 2011

Authors:

Jian Li Liu, Bao Qi Zuo

Keywords:

Contourlet Transform, Energy Based Signatures, Nonwovens, Support Vector Machine (SVM), Visual Quality Recognition

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] J. Militký, J. Rubnerová, V. Klicka: International Journal of Clothing Science and Technology, vol. 11(1999), pp.141-152.

Google Scholar

[2] J. Militký, V. Klicka: Journal of Information and Computing Science, vol. 2(2) (2007), pp.85-92.

Google Scholar

[3] J. L. Liu, B. Q. Zuo, X. Y. Zeng, P. Vroman, B. Rabenasolo: Expert Systems with Applications, vol. 37(3) (2010), pp.2241-2246.

DOI: 10.1016/j.eswa.2009.07.049

Google Scholar

[4] A. Cherkassky, A. Weinberg: Textile Research Journal, vol. 80(3) (2010), pp.226-235.

Google Scholar

[5] P. Payvandy, M. Yousefzadeh, M. Latifi: Journal of Textile Institute, vol. 101(1), (2010), pp.46-51.

Google Scholar

[6] M. N. Do, M. Vetterli: IEEE Transaction on Image Processing, vol. 14(12) (2005) pp.2091-2106.

Google Scholar

[7] D. D. Y. Po, M. N. Do: IEEE Transaction on Image Processing, vol. 15(6), (2006) pp.1610-1620.

Google Scholar

[8] R. Eslami, H. Radha: Proceedings of the International Conference on Image Processing (ICIP), 5(2004), p.3189–3192.

Google Scholar

[9] J. Chen, C. Wang, R. S. Wang: Neurocomputing, vol. 72, (2009) pp.3370-3375.

Google Scholar