OSA's Digital Library

Journal of Optical Technology

Journal of Optical Technology


  • Vol. 74, Iss. 10 — Oct. 1, 2007
  • pp: 694–699

Theoretico-informational approach to the introduction of feedback into multilevel machine-vision systems

A. S. Potapov  »View Author Affiliations

Journal of Optical Technology, Vol. 74, Issue 10, pp. 694-699 (2007)

View Full Text Article

Acrobat PDF (345 KB)

Browse Journals / Lookup Meetings

Browse by Journal and Year


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools



This paper discusses the problem of introducing feedback in multilevel machine-vision systems. Based on a theoretical-informational analysis, it is shown that feedback is needed in such systems because the individual components of the quality criterion common to the entire system are optimized at different levels. As a result, the decisions made at the earlier stages of the analysis use only part of the components of this criterion, and this makes these decisions less than optimal. An approach is proposed to introduce feedback as a method of achieving the global optimum of the informational quality criterion by iterative improvement of the decision. Based on these results, it is shown that the information contained in the contours is inadequate for a robust construction of the structural elements.

© 2007 Optical Society of America

A. S. Potapov, "Theoretico-informational approach to the introduction of feedback into multilevel machine-vision systems," J. Opt. Technol. 74, 694-699 (2007)

Sort:  Year  |  Journal  |  Reset


  1. A. Rares, M. J. T. Reinders, and E. A. Hendriks, "Image Interpretation Systems," Technical Report (MCCWS, TU Delft, 1999.
  2. A. Gove, S. Grossberg, and E. Mingolla, "Brightness perception, illusory contours, and corticogeniculate feedback," Visual Neurosci. 12, 1027 (1995).
  3. C.-E. Liedtke, O. Grau, and S. Growe, "Use of explicit knowledge for the reconstruction of 3-D object geometry," in International Conference on Computer Analysis of Images and Patterns, 1995, pp. 580-587.
  4. R. M. Kozlov, Adaptation and Training in Robotics (Nauka, Moscow, 1990).
  5. A. S. Potapov, Pattern Recognition and Machine Perception. General Approach Based on the Principle of Minimum Description Length (Politekhnika, St. Petersburg, 2007).
  6. S. Grossberg, "Adaptive pattern classification and universal recoding. I: Parallel development and coding of neural feature detectors," Biol. Cybern. 23, 121 (1976) S. Grossberg, and "II: Feedback, expectation, olfaction, and illusions," Biol. Cybern. 23, 187 (1976).
  7. S. Grossberg, "Adaptive resonance theory," Technical Report CAS/CNS TR-2000-024, in The Encyclopedia of Cognitive Science (Macmillan, London, 2003).
  8. S. K. Kopparapu and U. B. Desai, "Bayesian Approach to Image Interpretation," Springer International Series in Engineering and Computer Science, 2001, vol. 616.
  9. M. Li and P. Vitanyi, "Philosophical Issues in Kolmogorov complexity," Proc. ICALP92 (invited lecture), 1992, pp. 1-15.

Cited By

Alert me when this paper is cited

OSA is able to provide readers links to articles that cite this paper by participating in CrossRef's Cited-By Linking service. CrossRef includes content from more than 3000 publishers and societies. In addition to listing OSA journal articles that cite this paper, citing articles from other participating publishers will also be listed.

« Previous Article  |  Next Article »

OSA is a member of CrossRef.

CrossCheck Deposited