Browse > Article

Improved Statistical Grey-Level Models for PCB Inspection  

Bok, Jin Seop (Korea University of Technology and Education, School of Computer Engineering)
Cho, Tai-Hoon (Korea University of Technology and Education, School of Computer Engineering)
Publication Information
Journal of the Semiconductor & Display Technology / v.12, no.1, 2013 , pp. 1-7 More about this Journal
Abstract
Grey-level statistical models have been widely used in many applications for object location and identification. However, conventional models yield some problems in model refinement when training images are not properly aligned, and have difficulties for real-time recognition of arbitrarily rotated models. This paper presents improved grey-level statistical models that align training images using image or feature matching to overcome problems in model refinement of conventional models, and that enable real-time recognition of arbitrarily rotated objects using efficient hierarchical search methods. Edges or features extracted from a mean training image are used for accurate alignment of models in the search image. On the aligned position and orientation, fitness measure based on grey-level statistical models is computed for object recognition. It is demonstrated in various experiments in PCB inspection that proposed methods are superior to conventional methods in recognition accuracy and speed.
Keywords
statistical model; object recognition; template matching; image alignment; model refinement;
Citations & Related Records
연도 인용수 순위
  • Reference
1 T. Cootes, G. Page, C. Jackson, and C. Taylor, "Statistical grey-level models for object location and identification.", Image and Vision Computing, 14(8), pp. 533-540, 1996.   DOI   ScienceOn
2 T.F. Cootes, A. Hill, C.J. Taylor and J. Haslam, "The use of active shape models for locating structures in medical images", Image and Vision Computing, 12(6), pp. 355-366, July 1994.   DOI   ScienceOn
3 C. Liang-Chia, V. T. Nguyen and T. Abraham Mario "Automatic Optical Detection of Offset and Orientation of Electronic Component by Enhanced Active Shape Model (EASM)", American Scientific Publishers, vol. 20, pp. 1047-1055, 2012.
4 M. Turk and A. Pentland, "Eigenfaces for recognition. J. Cognitive", Neuroscience, 3(1), pp. 71-86, 1991.   DOI   ScienceOn
5 J. Haslam, C.J. Taylor and T.F. Cootes, "A probabalistic fitness measure for deformable template models", In E. Hancock (ed.), Proc. British Machine Vision Conference, BMVA Press, pp. 33-42, 1994
6 B. Efron and R. Tibshirani, "Bootstrap methods for standard errors, confidence intervals, and other measures of statistical accuracy", Statistical Science, 1(1), pp. 54-77, 1986.   DOI   ScienceOn
7 B. Moghaddam and A. Pentland, "Probabalistic visual learning for object detection" Proc. 5th Int. Conf. on Computer Vision, pp. 786-793, 1995.
8 R. Jain, R. Kasturi, and B.G. Schunck, "Machine Vision", McGraw-Hill, 1995.
9 C. Steger, "Similarity measures for occlusion, clutter, and illumination invariant object recognition", Ed. by B. Radig and S. Florczyk, Pattern Recognition, DAGM 2001, LNCS 2191, Springer Verlag, pp. 148- 154, 2001.