Automation and Remote Control

, Volume 77, Issue 3, pp 443–450

The maximal likelihood enumeration method for the problem of classifying piecewise regular objects

System Analysis and Operations Research

Abstract

We study the recognition problem for composite objects based on a probabilistic model of a piecewise regular object with thousands of alternative classes. Using the model’s asymptotic properties, we develop a new maximal likelihood enumeration method which is optimal (in the sense of choosing the most likely reference for testing on every step) in the class of “greedy” algorithms of approximate nearest neighbor search. We show experimental results for the face recognition problem on the FERET dataset. We demonstrate that the proposed approach lets us reduce decision making time by several times not only compared to exhaustive search but also compared to known approximate nearest neighbors techniques.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Pattern Recognition, Theodoridis, S. and Koutroumbas, K., Eds., Boston: Academic, 2008.Google Scholar
  2. 2.
    Hammerstrom, D.W. and Rehfuss, S., Neurocomputing Hardware: Present and Future, Artific. Intelligence Rev., 1993, vol. 7, no. 5, pp. 285–300.CrossRefGoogle Scholar
  3. 3.
    Abusev, R.A. and Lumel’skii, Ya.P., Statistical Models for Classifying Multidimensional Observations, Obozren. Prikl. Promyshl. Mat., 1996, vol. 3, no. 1, pp. 7–30.Google Scholar
  4. 4.
    Springer Handbook of Speech Recognition, Benesty, J., Sondh, M., and Huang, Y., Eds., New York: Springer, 2008.Google Scholar
  5. 5.
    Savchenko, A.V., Image as a Collection of Samples of Independent Identically Distributed Values of Features in Recognition Problems for Objects with Complex Structure, Zav. Lab. Diagnostika Materialov, 2014, vol. 80, no. 3, pp. 70–80.Google Scholar
  6. 6.
    Dalal, N. and Triggs, B., Histograms of Oriented Gradients for Human Detection, Proc. IEEE Conf. on Computer Vision & Pattern Recognition, San Diego, 2005, pp. 886–893.Google Scholar
  7. 7.
    Tan, X., Chen, S., Zhou, Z.H., et al., Face Recognition from a Single Image per Person: A Survey, Patt. Recognit., 2006, vol. 39, no. 9, pp. 1725–1745.CrossRefMATHGoogle Scholar
  8. 8.
    Silpa-Anan C. and Hartley, R., Optimised KD-trees for Fast Image Descriptor Matching, Proc. IEEE Conf. on Computer Vision & Pattern Recognition, Alaska, 2008, pp. 1–8.Google Scholar
  9. 9.
    Kullback, S., Information Theory and Statistics, New York: Dover, 1997.MATHGoogle Scholar
  10. 10.
    Borovkov, A.A., Matematicheskaya statistika. Dopolnitel’nye glavy (Mathematical Statistics. Additional Chapters), Moscow: Nauka, 1984.Google Scholar
  11. 11.
    Savchenko, A.V., Probabilistic Neural Network with Homogeneity Testing in Recognition of Discrete Patterns Set, Neural Networks, 2013, vol. 46, pp. 227–241.CrossRefMATHGoogle Scholar
  12. 12.
    Savchenko, A.V., Directed Enumeration Method in Image Recognition, Patt. Recognit., 2012, vol. 45, no. 8, pp. 2952–2961.CrossRefGoogle Scholar
  13. 13.
    Vidal, E., An Algorithm for Finding Nearest Neighbours in (Approximately) Constant Average Time, Patt. Recognit. Lett., 1986, vol. 4, no. 3, pp. 145–157.MathSciNetCrossRefGoogle Scholar
  14. 14.
    Gonzalez, E.C., Figueroa, K., and Navarro, G., Effective Proximity Retrieval by Ordering Permutations, IEEE Trans. PAMI, 2008, vol. 30, no. 9, pp. 1647–1658.CrossRefGoogle Scholar
  15. 15.
    Chen, C.C., Hierarchical Particle Swarm Optimization for Optimization Problems, Tamkang J. Sci. Eng., 2009, vol. 12, no. 3, pp. 289–298.Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2016

Authors and Affiliations

  1. 1.National Research University Higher School of EconomicsLaboratory of Algorithms and Technologies for Network AnalysisNizhny NovgorodRussia

Personalised recommendations