A Multi-scale Feature Likelihood Map for Direct Evaluation of Object Hypotheses⋆

  • Ivan Laptev
  • Tony Lindeberg
Conference paper
Part of the Lecture Notes in Computer Science 2106 book series (LNCS, volume 2106)


This paper develops and investigates a new approach for evaluating feature based object hypotheses in a direct way. The idea is to compute a feature likelihood map (FLM), which is a function normalized to the interval [0; 1], and which approximates the likelihood of image features at all points in scale-space. In our case, the FLM is defined from Gaussian derivative operators and in such a way that it assumes its strongest responses near the centers of symmetric blob-like or elongated ridge-like structures and at scales that reflect the size of these structures in the image domain. While the FLM inherits several advantages of feature based image representations, it also (i) avoids the need for explicit search when matching features in object models to image data, and (ii) eliminates the need for thresholds present in most traditional feature based approaches. In an application presented in this paper, the FLM is applied to simultaneous tracking and recognition of hand models based on particle filtering. The experiments demonstrate the feasibility of the approach, and that real time performance can be obtained by a pyramid implementation of the proposed concept.


Image Structure Scale Selection Object Hypothesis Simultaneous Tracking Local Image Structure 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Almansa, A. and Lindeberg, T. (2000). Fingerprint enhancement by shape adaptation of scale-space operators with automatic scale-selection, IEEE-IP, 9(12): 2027–2042.MathSciNetzbMATHGoogle Scholar
  2. Black, M. and Jepson, A. (1998). Eigen tracking: Robust matching and tracking of articulated objects using view-based representation, IJCV 26(1): 63–84.CrossRefGoogle Scholar
  3. Bretzner, L. and Lindeberg, T. (1999). Qualitative multi-scale feature hierarchies for object tracking, JVCIR 11: 115–129.Google Scholar
  4. Chomat, O., de Verdiere, V., Hall, D. and Crowley, J. (2000). Local scale selection for gaussian based description techniques, ECCV’00, Dublin, Ireland, 117–133.Google Scholar
  5. Crowley, J. and Sanderson, A. (1987). Multiple resolution representation and probabilistic matching of 2-D gray-scale shape, IEEE-PAMI 9(1): 113–121.CrossRefGoogle Scholar
  6. Fleck, M., Forsyth, D. and Bregler, C. (1996). Finding naked people, ECCV’96, Cambridge, UK, II:593–602.Google Scholar
  7. Florack, L.M.J. (1997). Image Structure, Kluwer.Google Scholar
  8. Isard, M. and Blake, A. (1996). Contour tracking by stochastic propagation of conditional density, ECCV’96, Cambridge, UK, I:343–356.Google Scholar
  9. Koenderink, J.J. and van Doorn, A.J. (1992). Generic neighborhood operators, IEEE-PAMI, 14(6): 597–605.CrossRefGoogle Scholar
  10. Laptev, I and Lindeberg, T. (2001) “A multi-scale feature likelihood map for direct evaluation of object hypotheses”, Technical report ISRN KTH/NA/P01/03-SE.
  11. Lindeberg, T. (1994). Scale-Space Theory in Computer Vision, Kluwer.Google Scholar
  12. Lindeberg, T. (1998). Feature detection with automatic scale selection, IJCV, 30(2): 77–116.Google Scholar
  13. Pizer, S.M., Burbeck, C.A., Coggins, J.M., Fritsch, D.S. and Morse, B.S. (1994). Object shape before boundary shape: Scale-space medial axis, JMIV 4: 303–313.CrossRefGoogle Scholar
  14. Schmid, C. and Mohr, R. (1997). Local grayvalue invariants for image retrieval, IEEE-PAMI 19(5): 530–535.CrossRefGoogle Scholar
  15. Shokoufandeh, A., Marsic, I. and Dickinson, S. (1999). View-based object recognition using saliency maps, IVC 17(5/6): 445–460.CrossRefGoogle Scholar
  16. Witkin, A.P. (1983). Scale-space filtering, Proc. IJCAI’83, Karlsruhe, West Germany, 1019–1022.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Ivan Laptev
    • 1
  • Tony Lindeberg
    • 1
  1. 1.Dept. of Numerical Analysis and Computing ScienceComputational Vision and Active Perception Laboratory (CVAP)StockholmSweden

Personalised recommendations