New Geometric Transform Based on Stochastic Geometry in the Context of Pattern Recognition

  • Nikolay Fedotov
  • Lyudmila Shulga
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)


Application of stochastic geometry methods to pattern recognition is analyzed. The paper is based on Trace-transforms of original images introduced by [1] into images on the Möbius band. The ability of a Trace-transform to solve such structuralistic problems as segmentation, analysis of objects’ relative position, and their number evaluation, is established. Feasibility of image nonlinear filtering through Trace-transforms is considered. Based on the new geometric transform, a new approach towards the construction of features, independent of images’ motions or their linear transforms, is put forward. A prominent characteristic of the group of features under consideration is that we can represent each of them as a consecutive composition of three functionals.


Original Image Decision Procedure Scanning Line Geometric Transform Recognition Feature 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Fedotov N.G., Metody Stokhasticheskoi Geometrii v Raspoznavanii Obrazov (Methods of Stochastic Geometry in Patters Recognition), Radio i Svjaz, Moscow (1990)Google Scholar
  2. 2.
    Fedotov N.G and Kadyrov A.A., Image Scanning in Machine Vision Leads to New Understanding of Image, Fifth Int Workshop on Digital Image Processing and Computer Graphics, Vol. 2363, Proc. SPIE (1994) 256–261Google Scholar
  3. 3.
    Kadyrov A.A and Fedotov N.G. Triple Features, Pattern Recognition and Image Analysis, Vol. 4 (1995)Google Scholar
  4. 4.
    Nikolay G. Fedotov, Lyudmila A. Shulga. New Ways to Form Features for Pattern Recognition on the Basis of Stochastic Geometry, 12th Scandinavian Conference on Image Analysis, Bergen, Vol. I.II, Norway, (2001) 373–380Google Scholar
  5. 5.
    Fedotov N.G., Shulga L.A. New Theory of Pattern Recognition on the Basis of Stochastic Geometry, WSCG’2000 Conference Proceedings, ISBN 80-7082-612-6, Vol. 1(2), (2000) 373–380Google Scholar
  6. 6.
    Nikolay G. Fedotov, Lyudmila A. Shulga. Enhancing Intellectual Power of Recognition Systems Based on New Pattern Recognition Theory, Proceedings 2002 IEEE International Conf. on Artificial Intelligence Systems (ICAIS 2002), IEEE Computer Society, Los Alamos, California, (2002) 192–197CrossRefGoogle Scholar
  7. 7.
    Fedotov N.G., Nikiforova T.V. Technicekaya defecktospopiya na osnove novoi teorii raspoznavaniay obrazov (Technical defectoscopy based on the new theory of pattern recognition), Measurement Technique, Vol.12, (2002) 27–31Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Nikolay Fedotov
    • 1
  • Lyudmila Shulga
  1. 1.Penza State UniversityPenzaRussia

Personalised recommendations