Title :
1D autoregressive modeling for defect detection in web inspection systems
Author :
Hajimowlana, S.H. ; Muscedere, R. ; Jullien, G.A. ; Roberts, J.W.
Author_Institution :
VLSI Res. Group, Windsor Univ., Ont., Canada
Abstract :
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
Keywords :
automatic optical inspection; autoregressive processes; computer vision; image texture; real-time systems; 1D autoregressive modeling; camera; defect detection; real-time data processing; web inspection systems; Cameras; Data processing; Digital signal processing chips; Field programmable gate arrays; Hardware; Image texture analysis; Inspection; Insulation life; Machine vision; Very large scale integration;
Conference_Titel :
Circuits and Systems, 1998. Proceedings. 1998 Midwest Symposium on
Conference_Location :
Notre Dame, IN
Print_ISBN :
0-8186-8914-5
DOI :
10.1109/MWSCAS.1998.759496
