1D autoregressive modeling for defect detection in web inspection systems

This paper discusses the application of 1D AR (autoregressive) method for defect detection in Web inspection systems. AR coefficients are obtained off-line and are used in real-time data processing. The algorithm was successfully simulated on synthesized and some real world defective samples. This method eliminates the need for traditional frame grabbers and can be implemented in minimum hardware mounted inside the camera.

[1]  S.M. Kay,et al.  Spectrum analysis—A modern perspective , 1981, Proceedings of the IEEE.

[2]  Graham A. Jullien,et al.  New design environment for defect detection in web inspection systems , 1997, Other Conferences.

[3]  Luc Van Gool,et al.  Texture analysis Anno 1983 , 1985, Comput. Vis. Graph. Image Process..

[4]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[5]  Sabine C. Mueller,et al.  Morphological image processing for the recognition of surface defects , 1994, Other Conferences.

[6]  Heikki Ailisto,et al.  Integrated machine vision technology for line-scan applications , 1997, Other Conferences.

[7]  M.G. Bellanger,et al.  Digital processing of speech signals , 1980, Proceedings of the IEEE.

[8]  Giuseppe Longobardi,et al.  Weaving defect detection by Fourier imaging , 1996, Other Conferences.