Local correlation and entropy maps as tools for detecting defects in industrial images

Ewa Skubalska-Rafajłowicz

International Journal of Applied Mathematics and Computer Science (2008)

  • Volume: 18, Issue: 1, page 41-47
  • ISSN: 1641-876X

Abstract

top
The aim of this paper is to propose two methods of detecting defects in industrial products by an analysis of gray level images with low contrast between the defects and their background. An additional difficulty is the high nonuniformity of the background in different parts of the same image. The first method is based on correlating subimages with a nondefective reference subimage and searching for pixels with low correlation. To speed up calculations, correlations are replaced by a map of locally computed inner products. The second approach does not require a reference subimage and is based on estimating local entropies and searching for areas with maximum entropy. A nonparametric estimator of local entropy is also proposed, together with its realization as a bank of RBF neural networks. The performance of both methods is illustrated with an industrial image.

How to cite

top

Ewa Skubalska-Rafajłowicz. "Local correlation and entropy maps as tools for detecting defects in industrial images." International Journal of Applied Mathematics and Computer Science 18.1 (2008): 41-47. <http://eudml.org/doc/207863>.

@article{EwaSkubalska2008,
abstract = {The aim of this paper is to propose two methods of detecting defects in industrial products by an analysis of gray level images with low contrast between the defects and their background. An additional difficulty is the high nonuniformity of the background in different parts of the same image. The first method is based on correlating subimages with a nondefective reference subimage and searching for pixels with low correlation. To speed up calculations, correlations are replaced by a map of locally computed inner products. The second approach does not require a reference subimage and is based on estimating local entropies and searching for areas with maximum entropy. A nonparametric estimator of local entropy is also proposed, together with its realization as a bank of RBF neural networks. The performance of both methods is illustrated with an industrial image.},
author = {Ewa Skubalska-Rafajłowicz},
journal = {International Journal of Applied Mathematics and Computer Science},
keywords = {defects detection; image processing; local correlation; entropy map},
language = {eng},
number = {1},
pages = {41-47},
title = {Local correlation and entropy maps as tools for detecting defects in industrial images},
url = {http://eudml.org/doc/207863},
volume = {18},
year = {2008},
}

TY - JOUR
AU - Ewa Skubalska-Rafajłowicz
TI - Local correlation and entropy maps as tools for detecting defects in industrial images
JO - International Journal of Applied Mathematics and Computer Science
PY - 2008
VL - 18
IS - 1
SP - 41
EP - 47
AB - The aim of this paper is to propose two methods of detecting defects in industrial products by an analysis of gray level images with low contrast between the defects and their background. An additional difficulty is the high nonuniformity of the background in different parts of the same image. The first method is based on correlating subimages with a nondefective reference subimage and searching for pixels with low correlation. To speed up calculations, correlations are replaced by a map of locally computed inner products. The second approach does not require a reference subimage and is based on estimating local entropies and searching for areas with maximum entropy. A nonparametric estimator of local entropy is also proposed, together with its realization as a bank of RBF neural networks. The performance of both methods is illustrated with an industrial image.
LA - eng
KW - defects detection; image processing; local correlation; entropy map
UR - http://eudml.org/doc/207863
ER -

References

top
  1. Altmann J. and Reitbock H.J.P. (1984). A fast correlation method for scale and translation invariant pattern recognition, IEEE Transactions an Pattern Analysis and Machine Intelligence 6(1): 46-57. 
  2. Beirlant J., Dudewicz E., Gyorfi L., van der Meulen EC (1997). Nonparametric entropy estimation: An overview, International Journal of Mathematical and Statistical Sciences 6(1): 17-39. Zbl0882.62003
  3. Bishop C.M. 1995. Neural Networks for Pattern Recognition, Oxford Press. Zbl0868.68096
  4. Brink A. D. and Pendock N. E. (1996). Minimum cross-entropy threshold selection, Pattern Recognition 29(1): 179-188. 
  5. Dong P., Bilbro G.L. and Mo-Yuen Chow (2006). Implementation of artificial neural network for real time applications using field programmable analog arrays, Procedings of the International Joint Conference on Neural Networks, Vancouver, BC, Canada, pp. 1518-1524. 
  6. Faugeras O. (1993). Three-Dimensional Computer Vision, MIT Press, Cambridge. 
  7. Forsyth D.A. and Ponce J. (2003). Computer Vision: Modern Approach, Prentice Hall, Upper Saddle River, NJ. 
  8. Goshtasby A., Gage S. H. and Bartolic J. F. (1984). A two-stage cross-correlation approach to template matching, IEEE Transactions on Pattern Analysis and Machine Intelligence 6(3): 374-378. 
  9. Haykin S. (1999). Neural Networks. A Comprehensive Foundation, 2nd Ed. Prentice Hall, Upper Saddle River, NJ. Zbl0934.68076
  10. Hero A.O. and Michel O.J.J. (1999). Asymptotic theory of greedy approximations to minimal-point random graphs, IEEE Transactions on Information Theory 45(6): 1921-1938. Zbl0945.90073
  11. Kittler J., Illingworth J. and Foglein J. (1985). Threshold selection based on a simple image statistic, Computer Vision, Graphics, and Image Processing 30(2): pp. 125-147. 
  12. Maher J., Mc Ginley B., Rocke P. and Morgan F. (2006). Intrinsic hardware evolution of neural networks in reconfigurable analogue and digital devices, Proceedings of 14th Annual Symposium on Field-Programmable Custom Computing Machines FCCM‘ 06, Napa, USA, pp. 321-322. 
  13. Mokkadem A. (1989). Estimation of the entropy and information of absolutely continuous random variables, IEEE Transactions on Information Theory 35(1): 193-196. Zbl0669.94004
  14. Otsu N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man and Cybernetics 9(1): 62-66. 
  15. Pal N.R. (1996). On minimum cross-entropy thresholding, Pattern Recognition 29(4): 575-580. 
  16. Ritter G.X. and Wilson J.N. (2001). Handbook of Computer Vision Algorithms in Image Algebra, 2nd Ed., CRC Press, Boca Raton, FL. Zbl0964.68145
  17. Pratt W.K. (2001). Digital Image Processing: PIKS Inside, 3rd Ed., John Wiley and Sons, New York. Zbl1303.68004
  18. Sezgin M. and Sankur B. (2004). Survey over image thresholding techniques and quantitative performance evaluation, Journal of Electronic Imaging 13(1): 146-168. 
  19. Tsai D., Lin Ch., and Chen J. (2003). The evolution of normalized cross correlation for defect detection, Pattern Recognition Letters 24(15): 2525-2535. Zbl1100.68613
  20. Zhu S.C., Wu Y. and Mumford D. (1997). Minimax entropy principle and its application to texture modeling, Neural Computation 9(8): 1627-1660. 
  21. Zhu S.C., Wu Y. Mumford D. (1998). Filters, random fields and maximum entropy (FRAME): Towards a unified theory for texture modeling, International Journal of Computer Vision 27(2): 107-126 . 

NotesEmbed ?

top

You must be logged in to post comments.