Advertisement

Improving Particle Segmentation from Process Images with Wiener Filtering

  • Lauri Laaksonen
  • Nataliya Strokina
  • Tuomas Eerola
  • Lasse Lensu
  • Heikki Kälviäinen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6688)

Abstract

While there is growing interest in in-line measurements of paper making processes, the factory environment often restricts the acquisition of images. The in-line imaging of pulp suspension is often difficult due to constraints to camera and light positioning, resulting in images with uneven illumination and motion blur. This article presents an algorithm for segmenting fibers from suspension images and studies the performance of Wiener filtering in improving the sub-optimal images. Methods are presented for estimating the point spread function and noise-to-signal ratio for constructing the Wiener filter. It is shown that increasing the sharpness of the image improves the performance of the presented segmentation method.

Keywords

pulp suspension fiber segmentation Wiener filtering machine vision image processing and analysis 

References

  1. 1.
    Allied Vision Technologies. Guppy Techical Manual (2009)Google Scholar
  2. 2.
    Buades, A., Coll, B., Morel, J.M.: A review of image denoising algorithms, with a new one. Multiscale Modeling and Simulation 4, 490–530 (2005)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Canny, J.: A computational approach to edge detection. IEEE Transactions of Pattern Analysis and Machine Intelligence 8, 679–698 (1986)CrossRefGoogle Scholar
  4. 4.
    Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM 24, 381–395 (1981)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Gonzales, R.C., Woods, R.E.: Digital Image Processing, 3rd edn. Pearson Prentice Hall, London (2008)Google Scholar
  6. 6.
    Lilliefors, H.W.: On the kolmogorov-smirnov test for normality with mean and variance unknown. Journal of the American Statistical Association 62, 399–402 (1967)CrossRefGoogle Scholar
  7. 7.
    Murphy, B.W., Carson, P.L., Ellis, J.H., Zhang, Y.T., Hyde, R.J., Chenevert, T.L.: Signal-to-noise measures for magnetic resonance imagers. Magnetic Resonance Imaging 2, 425–428 (1993)CrossRefGoogle Scholar
  8. 8.
    Szeliski, R., Joshi, N., Kriegman, D.J.: Psf estimation using sharp edge prediction. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2008)Google Scholar
  9. 9.
    Pang, M.-C.: A novel blind super-resolution technique based on the improved poisson maximum a posteriori algorithm. International Journal of Imaging Systems and Technology 12, 239–246 (2002)CrossRefGoogle Scholar
  10. 10.
    Robertson, G., Olson, J., Allen, P., Chan, B., Seth, R.: Measurement of fiber length, coarseness, and shape with the fiber quality analyzer. Tappi Journal 82, 93–98 (1999)Google Scholar
  11. 11.
    Saarela, J., Törmänen, M., Myllylä, R.: Measuring pulp consistency and fines content with a streak camera. Measurement Science and Technology 14, 1801–1806 (2003)CrossRefGoogle Scholar
  12. 12.
    Sitholé, B., Filion, D.: Assessment of methods for the measurement of macrostickies in recycled pulps. Progress in Paper Recycling 17 (2008)Google Scholar
  13. 13.
    Wang, F., Hubbe, M.: Development and evaluation of an automated streaming potential measurement device. Colloids and Surfaces A: Physicochemical and Engineering Aspects 194, 221–232 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Lauri Laaksonen
    • 1
  • Nataliya Strokina
    • 1
  • Tuomas Eerola
    • 1
  • Lasse Lensu
    • 1
  • Heikki Kälviäinen
    • 1
  1. 1.Machine Vision and Pattern Recognition Laboratory (MVPR) Department of Information TechnologyLappeenranta University of Technology (LUT)LappeenrantaFinland

Personalised recommendations