Minimum description length principle in the field of image analysis and pattern recognition

  • A. S. PotapovEmail author
Plenary Papers


Problems of decision criterion in the tasks of image analysis and pattern recognition are considered. Overlearning as a practical consequence of fundamental paradoxes in inductive inference is illustrated with examples. Theoretical (on the base of algorithmic complexity) and practical formulations of the minimum description length (MDL) principle are given. Decrease of the overlearning effect is shown in the examples of modern recognition, grouping, and segmentation methods modified with the MDL principle. Novel possibilities of construction of learnable image analysis algorithms by representation optimization on the base of the MDL principle are described.


Inductive Inference Minimum Description Length Algorithmic Probability Universal Turing Machine Vavilov State Optical Institute 
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.
    T. Lee, “A Minimum Description Length Based Image Segmentation Procedure, and Its Comparison with a Cross-Validation Based Segmentation Procedure,” J. Am. Stat. Assoc. 95, 259–270 (2000).zbMATHCrossRefGoogle Scholar
  2. 2.
    M. Li and P. Vitanyi, “Philosophical Issue in Kolmogorov Complexity,” in Proc. ICALP’92 (Vienna, 1992), pp. 1–15.Google Scholar
  3. 3.
    U. von Luxburg, O. Bousquet, and B. Schölkopf, “A Compression Approach to Support Vector Model Selection,” Mach. Learn. Res. 5, 293–323 (2004).Google Scholar
  4. 4.
    A. S. Potapov, I. A. Malyshev, A. E. Puysha, and A. N. Averkin, “New Paradigm of Learnable Computer Vision Algorithms Based on the Rsepresentational MDL Principle,” Proc. SPIE 7696, 769606 (2010).CrossRefGoogle Scholar
  5. 5.
    J. J. Rissanen, “Modeling by the Shortest Data Description,” Automat. J. IFAC 14, 465–471 (1978).zbMATHCrossRefGoogle Scholar
  6. 6.
    M. Sato, M. Kudo, J. Toyama, and M. Shimbo, “Construction of a Nonlinear Discrimination Function Based on the MDL Criterion,” in Proc. 1st Workshop on Stat. Techniques in Pattern Recognition (Prague, 1997), pp. 141–146.Google Scholar
  7. 7.
    R. Solomonoff, Does Algorithmic Probability Solve the Problem of Induction? (Cambridge MA, 1997).Google Scholar
  8. 8.
    H. Tenmoto, M. Kudo, and M. Shimbo, “MBL-Based Selection of the Number of Components in Mixture Models for Pattern Classification,” Adv. Pattern Recogn., No. 1451, 831–836 (1998).Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2011

Authors and Affiliations

  1. 1.Vavilov State Optical InstituteSt. PetersburgRussia

Personalised recommendations