Higher Order Image Pyramids

  • Joshua Gluckman
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3952)


The scale invariant property of an ensemble of natural images is examined which motivates a new early visual representation termed the higher order pyramid. The representation is a non-linear generalization of the Laplacian pyramid and is tuned to the type of scale invariance exhibited by natural imagery as opposed to other scale invariant images such as 1/f correlated noise and the step edge. The transformation of an image to a higher order pyramid is simple to compute and straightforward to invert. Because the representation is invertible it is shown that the higher order pyramid can be truncated and quantized with little loss of visual quality. Images coded in this representation have much less redundancy than the raw image pixels and decorrelating transformations such as the Laplacian pyramid. This is demonstrated by showing statistical independence between pairs of coefficients. Because the representation is tuned to the ensemble redundancies the coefficients of the higher order pyramid are more efficient at capturing the variation within the ensemble which leads too improved matching results. This is demonstrated on two recognition tasks, face recognition with illumination changes and object recognition which viewpoint changes.


Face Recognition Scale Invariance Natural Image Illumination Change Step Edge 
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. 1.
    van Hateren, J.: Independent component filters of natural images compared with simple cells. Proc. of the R. Stat. Soc. of London B 265, 359–366 (1998)CrossRefGoogle Scholar
  2. 2.
    Attneave, F.: Some informational aspects of visual perception. Psych. Rev. 61, 183–193 (1954)CrossRefGoogle Scholar
  3. 3.
    Barlow, H.: Possible principles underlying the transformaiton of senosry messages. In: Sensory Commuincation, MIT Press, Cambridge (1961)Google Scholar
  4. 4.
    Zhu, S.: Statistical modeling and coneptualization of visual patterns. IEEE Trans. on Pattern Analaysis and Machine Intelligence 25, 691–712 (2003)CrossRefGoogle Scholar
  5. 5.
    Burt, P., Adelson, E.: The laplacian pyramid as a compact image code. IEEE Trans. on Communications. 31, 532–540 (1983)CrossRefGoogle Scholar
  6. 6.
    Field, D.: Relations between the statistics of natural images and the response properties of cortical cells. J. of the Opt. Soc. of Am. A 4, 23–79 (1987)CrossRefGoogle Scholar
  7. 7.
    Ruderman, D.: The statistics of natural images. Network 5, 477–500 (1993)Google Scholar
  8. 8.
    Zhu, S., Mumford, D.: Prior learning and gibbs reactionn-diffusion. IEEE Trans. on Pattern Analysis and Machine Intelligence 19, 12–36 (1997)Google Scholar
  9. 9.
    Simoncelli, E., Adelson, E.: Noise removal via bayesian wavelet coding. In: Int’l Conf. on Image Processing, pp. 379–382 (1996)Google Scholar
  10. 10.
    Simoncelli, E., Freeman, W.: The steerable pyramid: A flexible architecture for multi-scale derivative computation. In: Int’l Conf. on Image Processing (1995)Google Scholar
  11. 11.
    Buccigrossi, R., Simoncelli, E.: Image compression via joint statistical characterization in the wavelet domain. IEEE Trans. on Image Processing 8, 16–88 (1999)CrossRefGoogle Scholar
  12. 12.
    Schwartz, O., Simoncelli, E.: Natural signal statistics and sensory gain control. Nature Neuroscience 4, 819–825 (2001)CrossRefGoogle Scholar
  13. 13.
    Chen, H., Belhumeur, P., Jacobs, D.: In search of illumination invariants. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (2000)Google Scholar
  14. 14.
    Geusebroek, J., Burghouts, G., Smeulders, A.: The amsterdam library of object images. Int’l J. Computer Vision 61, 103–112 (2005)CrossRefGoogle Scholar
  15. 15.
    Olshausen, B., Field, D.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381, 607–609 (1996)CrossRefGoogle Scholar
  16. 16.
    Bell, A., Sejnowski, T.: The independent components of natural scenes are edge filters. Vision Research 37, 3327–3338 (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Joshua Gluckman
    • 1
  1. 1.Dept. of Computer and Information SciencePolytechnic UniversityBrooklynUSA

Personalised recommendations