Skip to main content
SpringerLink
Log in

A generalisation of model selection criteria

  • Original Article
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

In this article we generalise some of the existing model selection criteria used in statistics and computer vision. Model selection criteria are mostly used to decide which model is more appropriate for explaining a specific data set. We adapt these criteria in a way that they can be used for the evaluation of models fitted to different data sets and for the evaluation of sets of models. We found this adaption especially useful in situations where we have a set of models with domains that may overlap and where we need to find an optimal subset of models for explaining the whole data set. Adapted model selection criteria were then succesfully used in range image segmentation application (reverse engineering), based on the recover-and-select paradigm.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4. a-b a
Fig. 5.
Fig. 6.
Fig. 7.
Fig. 8.
Fig. 9.
Fig. 10.
Fig. 11.
Fig. 12.
Fig. 13.
Fig. 14.

Similar content being viewed by others

References

  1. Bajcsy R, Lee SW, Leonardis A (1996) Detection of diffuse and specular interface reflections and inter-reflections by color image segmentation. Int J Comp Vis 17:241–272

    Google Scholar 

  2. Xu L, Jackowski M, Goshtasby A, Yu C, Roseman D, Bines S, Dhawan A, Huntley A (1999) Segmentation of skin cancer images. Imag Vis Comp 17(1):65–74

    Article  MATH  Google Scholar 

  3. Lukäcs G, Marshall AD, Martin RR (1998) Faithful least-squares fitting of spheres, cylinders, cones and tori for reliable segmentation. In: Proceedings of the 5th European Conference on Computer Vision, Freiburg, Germany, June 1998

  4. Leonardis A, Gupta A, Bajcsy R (1995) Segmentation of range images as the search for geometric parametric models. Int J Comp Vis 14:253–277

    Google Scholar 

  5. Bolles RC, Fischer MA (1981) A RANSAC-based approach to model fitting and its applications to finding cylinders in range data. IJCAI 637–643

  6. Besl PJ, Jain RC (1988) Segmentation through variable-order surface fitting. IEEE Trans PAMI 10:167–192

    Article  Google Scholar 

  7. Akaike H (1973) Information theory and an extension of the maximum likelihood principle. In: Petrov BN, Csaki F (eds) 2nd international Symposium of Information Theory

  8. Kanatani K (1998) Geometric information criterion for model selection. Int J Comp Vis 26(3):171–189

    Article  Google Scholar 

  9. Bozdogan H (1987) Model selection and Akaike”s information criterion (AIC): the general theory and its analytical extensions. Psychometrika 52:345–370

    MathSciNet  MATH  Google Scholar 

  10. Rissanen J (1978) Modelling by shortest data description. Automatica 14:468–471

    Article  Google Scholar 

  11. Schwarz G (1978) Estimating the dimension of the model. Annal Stat 6:461–464

    MATH  Google Scholar 

  12. Jakli A, Leonardis A, Solina F (1996) Segmentor: an object-oriented framework for image segmentation. In: Proceedings of the 3rd Slovenian-German and the 2nd SDRV Workshop, Ljubljana, Slovenia, April 1996

  13. Boyer KL, Mirza MJ, Ganguly G (1994) The robust sequential estimator: a general approach and its applications to surface organization in range data. IEEE Patt Anal Mach Intell 16(10):987–1001

    Article  Google Scholar 

  14. Leclerc YG (1989) Constructing simple stable descriptions for image partitioning. Int J Comp Vis 3(1):73–102

    MATH  Google Scholar 

  15. Bubna K, Stewart CV (1998) Model selection and surface merging in reconstruction algorithms. In: Proceedings of the International Conference on Computer Vision, Bombay, India, January 1998

  16. Bubna K, Stewart CV (2000) Model selection techniques and merging rules for range data segmentation algorithms. Comp Vis Imag Underst 80:215–245

    Article  MATH  Google Scholar 

  17. Kverh B (2001) Selection of parametric models in data segmentation framework. Dissertation, University of Ljubljana

  18. Jakli A (1997) Construction of CAD models from range images. Dissertation, University of Ljubljana

  19. Leonardis A, Jakli A, Solina F (1997) Superquadrics for segmenting and modeling range data. IEEE Trans PAMI 9(11):1289–1295

    Google Scholar 

  20. Glover F, Laguna M (1997) Tabu search. Kluwer, Boston, MA

  21. Hoover A, Jean-Baptiste G, Jiang X, Flynn PJ, Bunke H, Goldgof DB, Bowyer K, Eggert DW, Fitzgibbon A, Fisher RB (1996) An experimental comparison of range image segmentation algorithms. IEEE Trans PAMI 18(7):673–689

    Article  Google Scholar 

  22. Efron B, Tibshirani R (1993) An Introduction to Bootstrap. Chapman-Hall, New York

  23. Solina F, Leonardis A (1998) Proper scale for modeling visual data. Imag Vis Comp 16:89–98

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty for Computer and Information Science, University of Ljubljana, Traška 25, 1001, Ljubljana, Slovenia

    B. Kverh & Aleš Leonardis

Authors
  1. B. Kverh
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Aleš Leonardis
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to B. Kverh.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kverh, B., Leonardis, A. A generalisation of model selection criteria. Pattern Anal Applic 7, 51–65 (2004). https://doi.org/10.1007/s10044-004-0206-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-004-0206-5

Keywords

Search

Navigation