Skip to main content
SpringerLink
Log in

Incremental Computation of Feature Hierarchies

  • Conference paper
Pattern Recognition (DAGM 2010)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 6376))

Included in the following conference series:

Abstract

Feature hierarchies are essential to many visual object recognition systems and are well motivated by observations in biological systems. The present paper proposes an algorithm to incrementally compute feature hierarchies. The features are represented as estimated densities, using a variant of local soft histograms. The kernel functions used for this estimation in conjunction with their unitary extension establish a tight frame and results from framelet theory apply. Traversing the feature hierarchy requires resampling of the spatial and the feature bins. For the resampling, we derive a multi-resolution scheme for quadratic spline kernels and we derive an optimization algorithm for the upsampling. We complement the theoretic results by some illustrative experiments, consideration of convergence rate and computational efficiency.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nature Neuroscience 2(11), 1019–1025 (1999)

    Article  Google Scholar 

  2. Granlund, G.H., Knutsson, H.: Signal Processing for Computer Vision. Kluwer Academic Publishers, Dordrecht (1995)

    Google Scholar 

  3. Serre, T., Wolf, L., Poggio, T.: Object recognition with features inspired by visual cortex. In: Computer Vision and Pattern Recognition, pp. 994–1000 (2005)

    Google Scholar 

  4. Mutch, J., Lowe, D.G.: Multiclass object recognition with sparse, localized features. In: Computer Vision and Pattern Recognition, pp. 11–18 (2006)

    Google Scholar 

  5. Grauman, K., Darrell, T.: The pyramid match kernel: Discriminative classification with sets of image features. In: Intern. Conf. Computer Vision, pp. 1458–1465 (2005)

    Google Scholar 

  6. Felsberg, M.: Spatio-featural scale-space. In: Tai, X.-C., Mørken, K., Lysaker, M., Lie, K.-A. (eds.) Scale Space and Variational Methods in Computer Vision. LNCS, vol. 5567, pp. 808–819. Springer, Heidelberg (2009)

    Google Scholar 

  7. Pouget, A., Dayan, P., Zemel, R.: Information processing with population codes. Nature Reviews – Neuroscience 1, 125–132 (2000)

    Article  Google Scholar 

  8. Snippe, H.P., Koenderink, J.J.: Discrimination thresholds for channel-coded systems. Biological Cybernetics 66, 543–551 (1992)

    Article  MATH  Google Scholar 

  9. Howard, I.P., Rogers, B.J.: Binocular Vision and Stereopsis. OUP, Oxford (1995)

    Google Scholar 

  10. Granlund, G.H.: An associative perception-action structure using a localized space variant information representation. In: Sommer, G., Zeevi, Y.Y. (eds.) AFPAC 2000. LNCS, vol. 1888, pp. 48–68. Springer, Heidelberg (2000)

    Chapter  Google Scholar 

  11. Felsberg, M., Forssén, P.E., Scharr, H.: Channel smoothing: Efficient robust smoothing of low-level signal features. IEEE PAMI 28(2), 209–222 (2006)

    Google Scholar 

  12. Granlund, G.H.: In search of a general picture processing operator. Computer Graphics and Image Processing 8, 155–173 (1978)

    Article  Google Scholar 

  13. Burt, P.J., Adelson, E.H.: The Laplacian pyramid as a compact image code. IEEE Trans. Communications 31(4), 532–540 (1983)

    Article  Google Scholar 

  14. Mallat, S.G.: A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans. Pattern Analysis Machine Intelligence 11, 674–693 (1989)

    Article  MATH  Google Scholar 

  15. Daubechies, I.: Orthonormal bases of compactly supported wavelets. Communications on Pure and Applied Mathematics 41(7), 909–996 (1988)

    Article  MATH  MathSciNet  Google Scholar 

  16. Chan, R.H., Shen, Z., Xia, T.: A framelet algorithm for enhancing video stills. Applied and Computational Harmonic Analysis 23(2), 153–170 (2007)

    Article  MATH  MathSciNet  Google Scholar 

  17. Jonsson, E., Felsberg, M.: Efficient computation of channel-coded feature maps through piecewise polynomials. Image and Vision Comp. 27(11), 1688–1694 (2009)

    Article  Google Scholar 

  18. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)

    Article  Google Scholar 

  19. Petukhov, A.: Symmetric framelets. Constr. Approx 19, 309–328 (2000)

    Article  MathSciNet  Google Scholar 

  20. Chan, R.H., Riemenschneider, S.D., Shen, L., Shen, Z.: Tight frame: an efficient way for high-resolution image reconstruction. ACHA 17(1), 91–115 (2004)

    MATH  MathSciNet  Google Scholar 

  21. Chui, C.K., He, W.: Compactly supported tight frames associated with refinable functions. Applied and Computational Harmonic Analysis 8(3), 293–319 (2000)

    Article  MATH  MathSciNet  Google Scholar 

  22. Sonka, M., Hlavac, V., Boyle, R.: Image Processing, Analysis, and Machine Vision. Thomson-Engineering (2007)

    Google Scholar 

  23. Vikstén, F., Forssén, P.E., Johansson, B., Moe, A.: Comparison of local image descriptors for full 6 degree-of-freedom pose estimation. In: IEEE ICRA (2009)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical Engineering, Linköping University, Sweden

    Michael Felsberg

Authors
  1. Michael Felsberg
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. GRIS, TU Darmstadt, Fraunhoferstr. 5, 64283, Darmstadt, Germany

    Michael Goesele  & Stefan Roth  & 

  2. Fraunhofer Institute for Computer Graphics Research (IGD), Fraunhoferstr. 5, 64283, Darmstadt, Germany

    Arjan Kuijper

  3. Dept. of Computer Science, TU Darmstadt, Hochschulstrasse 10, 64289, Darmstadt, Germany

    Bernt Schiele

  4. TU Darmstadt, Hochschulstr. 10, 64289, Darmstadt, Germany

    Konrad Schindler

Rights and permissions

Reprints and permissions

Copyright information

© 2010 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Felsberg, M. (2010). Incremental Computation of Feature Hierarchies. In: Goesele, M., Roth, S., Kuijper, A., Schiele, B., Schindler, K. (eds) Pattern Recognition. DAGM 2010. Lecture Notes in Computer Science, vol 6376. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15986-2_53

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-15986-2_53

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-15985-5

  • Online ISBN: 978-3-642-15986-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation