Synthesis of Optimal differentiators for the locally oriented texture detection algorithm
I.S. Gruzman

Full text of article: Russian language.

Abstract:
A method is proposed for constructing noise-resistant mask differentiating filters minimizing error probability in locally oriented texture detection algorithm based on gradient structure tensor. A gaussian approximation of the components joint distribution of the gradient structure tensor is proposed to solve the problem of synthesizing.
It is shown that a decrease in the systematic error leads to a considerable increase in the accuracy of directional field estimation. It is shown that the use of optimal mask differentiating filter greatly reduces the probability of error detection.

Key words:
oriented texture, gradient structure tensor , mask differentiating filter, error detection.

References:

  1. Vliet, L. Estimators for Orientation and Anisotropy in Digitized Images / L. Vliet, P. Verbeek // Proc. First Annual Conference of the “Advanced School for Computing and Imaging” – ASCI’95, Heijen, NL, May 16-18, 1995. – P. 442-450.
  2. Maltoni, D. Handbook of Fingerprint Recognition / D. Maltoni, D. Maio, A.K. Jain, S. Prabhakar. – NY: Sprin­ger-Verlag, 2009. – 496 p.
  3. Methods of Computer Images Processing (Secondary Edition) / edited by V.A. Soifer. –  Ìoscow: “Fizmatlit” Publisher, 2003. – 784 p. – ISBN 5-9221-0270-2. – (In Russian).
  4. Gruzman, I.S. Anisotropic image segmentation based on local spectral characteristics / I.S. Gruzman, K.V. Novikov // Avtometriya. – 2004. – V. 40, N 6. – P. 23-28. – ISSN 0320-7102. – (In Russian).
  5. Roli, F. Measure of texture anisotropy for crack detection on textured surfaces / F. Roli // Electronics Letters. – 1996. – V. 32, N 14. – P. 1274-1275.
  6. Bigun, J. Vision with Direction: A systematic introduction to image processing and computer vision / J. Bigun. – Berlin: Springer-Verlag, 2006. – 396 p.
  7. Jahne, B. Digital Image processing / B. Jahne.– NY: Springer-Verlag, 2005. – 607 p.
  8. Gruzman, I.S. Analysis of Systematic Errors of Algorithm of Constructing Directional Field Based on Spectral Characteristics / I.S. Gruzman, V.B. Karpushin // Doklady Akad. Nauk Vyssh. Shkoly Ros. Feder. – 2008. – N 1. – P. 73- 82. – ISSN 1727-2769. – (In Russian).
  9. Gruzman, I.S. Synthesis of Gradient Algorithms with the Minimum Systematic Error in Estimating Directional Fields / I.S. Gruzman, V.B. Karpushin // Avtometriya. – 2010. – V. 46, N 1. – P. 1-8. – ISSN 0320-7102. – (In Russian).
  10. Feng, X. Multiscale Principal Components Analysis for Image Local Orientation Estimation / X. Feng, P. Milanfar // Proc. of the 36th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA. – 2002, November. –V. 1. – P. 478-482.
  11. Gruzman, I.S. Fast Algorithm of Segmentation of Anisotropic Images Based on Local Spectral Characteristics / I.S. Gruzman, K.V. Novikov // Izv. Vyssh. Uchebn. Za­ved. Rossii, Ser. Radioelektronika. – 2005. – N 3. – P. 50-56. – ISSN 1993-8985. – (In Russian)
  12. Dudgeon, D.E. Multidimensional Digital Signal Processing / D.E. Dudgeon, R.M. Mersereau. – New Jersey: Prentice-Hall, 1984. – 488 p.
© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; E-mail: ko@smr.ru; Phones: +7 (846) 332-56-22, Fax: +7 (846) 332-56-2