Development of a real-time machine vision system for detecting defeats of cord fabrics

Automatic detection techniques based on machine vision can be used in fabric industry for quality control, which constantly pursues intelligent methods to replace human inspections of product. This work introduces the principle components of a real-time machine vision system for defeat detection of cord fabrics, which is usually a challenging task in practice. The work aims at solving some difficulties usually incurring in such kind of tasks. The design and implementation of the algorithm, software and hardware are introduced. Based on the Gabor wavelet techniques, the system can automatically detect regular texture defects. Our experiments show the proposed algorithm is favorably suited for detecting several types of cord fabric defects. The system testing has been carried in both on-line and off-line situations. The corresponding results show the system has good performance with high detection accuracy, quick response and strong robustness.

[1]  Sundaresan Jayaraman,et al.  FDICS: A Vision-based System for the Identification and Classification of Fabric Defects , 1998 .

[2]  Aura Conci,et al.  A fractal image analysis system for fabric inspection based on a box-counting method , 1998, Comput. Networks.

[3]  N. H. C. Yung,et al.  Fabric defect detection using adaptive wavelet , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[4]  David Casasent,et al.  Real, imaginary, and clutter Gabor filter fusion for detection with reduced false alarms , 1994 .

[5]  Shih-hsuan Chiu,et al.  Textural Defect Segmentation Using a Fourier-Domain Maximum Likelihood Estimation Method , 2002 .

[6]  James S. Goddard,et al.  Vision system for on-loom fabric inspection , 1999 .

[7]  Chung-Feng Jeffrey Kuo,et al.  Gray Relational Analysis for Recognizing Fabric Defects , 2003 .

[8]  S. Ozdemir,et al.  Markov random fields and Karhunen-Loeve transforms for defect inspection of textile products , 1996, Proceedings 1996 IEEE Conference on Emerging Technologies and Factory Automation. ETFA '96.

[9]  G. Pang,et al.  Identification of surface defects in textured materials using wavelet packets , 2001, Conference Record of the 2001 IEEE Industry Applications Conference. 36th IAS Annual Meeting (Cat. No.01CH37248).

[10]  Domenec Puig,et al.  Pixel Classification by Divergence-Based Integration of Multiple Texture Methods and Its Application to Fabric Defect Detection , 2003, DAGM-Symposium.

[11]  Sungshin Kim,et al.  Wavelet analysis to fabric defects detection in weaving processes , 1999, ISIE '99. Proceedings of the IEEE International Symposium on Industrial Electronics (Cat. No.99TH8465).

[12]  黄秀宝,et al.  Fabric Defect Detection Using GMRF Model , 1999 .

[13]  I. Tsai,et al.  Fabric Inspection Based on Best Wavelet Packet Bases , 2000 .

[14]  Shih-hsuan Chiu,et al.  Defect Segmentation of Texture Images with Wavelet Transform and a Co-occurrence Matrix , 2001 .

[15]  Ajay Kumar,et al.  Fabric defect segmentation using multichannel blob detectors , 2000 .