An Adaptive Segmentation Method for Product Surface Inspection

Aiming at the specialty and practical requirement in on-line visual inspection of industrial product surface, an adaptive segmentation algorithm using bi-threshold selection method based on Otsu method is presented. For a gray image with two main peaks in its histogram, the target peak was extracted with two thresholds, which could segment the product surface from background and possibly existed defects. The second threshold was determined under the help of an artificial peak made in a way given in this paper. The experiment results indicate that the proposed method has low computation cost, fast speed and good segmentation performance

[1]  Jiaoyan Ai,et al.  Analysis and detection of ceramic-glass surface defects based on computer vision , 2002, Proceedings of the 4th World Congress on Intelligent Control and Automation (Cat. No.02EX527).

[2]  Bülent Sankur,et al.  Survey over image thresholding techniques and quantitative performance evaluation , 2004, J. Electronic Imaging.

[3]  Rangachar Kasturi,et al.  Machine vision , 1995 .

[4]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[5]  Yi Lu Murphey,et al.  An intelligent real-time vision system for surface defect detection , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[6]  E. Deutschl,et al.  Defect detection on rail surfaces by a vision based system , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[7]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[8]  Milan Sonka,et al.  Image pre-processing , 1993 .

[9]  P.K Sahoo,et al.  A survey of thresholding techniques , 1988, Comput. Vis. Graph. Image Process..