Sum-of-Superellipses – A Low Parameter Model for Amplitude Spectra of Natural Images

  • Marcel Spehr
  • Stefan Gumhold
  • Roland W. Fleming
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6978)

Abstract

Amplitude spectra of natural images look surprisingly alike. Their shape is governed by the famous 1/f power law. In this work we propose a novel low parameter model for describing these spectra. The Sum-of-Superellipses conserves their common falloff behavior while simultaneously capturing the dimensions of variation—concavity, isotropy, slope, main orientation—in a small set of meaningful illustrative parameters. We demonstrate its general usefulness in standard computer vision tasks like scene recognition and image compression.

Keywords

Natural images image statistics amplitude spectrum Lamé curve superellipse image retrieval 

References

  1. [BM87]
    Burton, G.J., Moorhead, I.R.: Color and spatial structure in natural scenes. Applied Optics 26(1), S. 157–S. 170 (1987) ISSN 1539–4522CrossRefGoogle Scholar
  2. [BS02]
    Buccigrossi, R.W., Simoncelli, E.P.: Image compression via joint statistical characterization in the wavelet domain. IEEE Transactions on Image Processing 8(12), S. 1688–S. 1701 (2002) ISSN 1057–7149CrossRefGoogle Scholar
  3. [Fie87]
    Field, D.J.: Relations between the statistics of natural images and the response properties of cortical cells. J. Opt. Soc. Am. A 4(12), S. 2379–S. 2394 (1987)CrossRefGoogle Scholar
  4. [GCP+04]
    Guyader, N., Chauvin, A., Peyrin, C., Hérault, J., Marendaz, C.: Image phase or amplitude? Rapid scene categorization is an amplitude-based process. Comptes Rendus-Biologies 327(4), S. 313–S. 318 (2004)CrossRefGoogle Scholar
  5. [HBS92]
    Hancock, P.J.B., Baddeley, R.J., Smith, L.S.: The principal components of natural images. Network: Computation in Neural Systems 3(1), S. 61–S. 70 (1992)CrossRefGoogle Scholar
  6. [HS98]
    van Hateren, J.H., van der Schaaf, A.: Independent component filters of natural images compared with simple cells in primary visual cortex.. Proceedings of the Royal Society B: Biological Sciences 265(1394), S. 359 (1998)CrossRefGoogle Scholar
  7. [KK10]
    Kim, K.I., Kwon, Y.: Single-Image Super-Resolution Using Sparse Regression and Natural Image Prior. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(6), S. 1127–S. 1133 (2010) ISSN 0162–8828CrossRefGoogle Scholar
  8. [LSK+07]
    Liu, C., Szeliski, R., Kang, S.B., Zitnick, C.L., Freeman, W.T.: Automatic estimation and removal of noise from a single image. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(2), S. 299–S. 314 (2007) ISSN 0162–8828CrossRefGoogle Scholar
  9. [MCCN77]
    Mezrich, J.J., Carlson, C.R., Cohen, R.W.: NJ, RCA LABS P.: Image descriptors for displays (1977)Google Scholar
  10. [MSS02]
    Manjunath, B.S., Salembier, P., Sikora, T.: Introduction to MPEG-7: multimedia content description interface. John Wiley & Sons Inc., Chichester (2002) ISBN 0471486787Google Scholar
  11. [OF96]
    Olshausen, B.A., Field, D.J.: Natural image statistics and efficient coding*. Network: Computation in Neural Systems 7(2), S. 333–S. 339 (1996) ISSN 0954–898XCrossRefGoogle Scholar
  12. [OT01]
    Oliva, A., Torralba, A.B.: Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope. International Journal of Computer Vision 42(3), S. 145–S. 175 (2001)CrossRefMATHGoogle Scholar
  13. [OTDH99]
    Oliva, A., Torralba, A., Dugue, A.G., Herault, J.: Global semantic classification of scenes using power spectrum templates (1999)Google Scholar
  14. [RB94]
    Ruderman, D.L., Bialek, W.: Statistics of natural images: Scaling in the woods. Physical Review Letters 73(6), S. 814–S. 817 (1994)CrossRefGoogle Scholar
  15. [Red07]
    Redies, C.: A universal model of esthetic perception based on the sensory coding of natural stimuli. Spatial Vision, 21 1(2), S. 97–S. 117 (2007) ISSN 0169–1015CrossRefGoogle Scholar
  16. [RSAT04]
    Reinhard, E., Shirley, P., Ashikhmin, M., Troscianko, T.: Second order image statistics in computer graphics. In: Proceedings of the 1st Symposium on Applied Perception in Graphics and Visualization, pp. S. 99–S. 106 (2004)Google Scholar
  17. [Rud97]
    Ruderman, D.L.: Origins of scaling in natural images. Vision Research 37(23), S. 3385–S. 3398 (1997)CrossRefGoogle Scholar
  18. [SH96]
    van der Schaaf, A., van Hateren, J.: Modelling the power spectra of natural images: Statistics and information. Vision Research 36(17), S. 2759–S. 2770 (1996)CrossRefGoogle Scholar
  19. [SWF09]
    Spehr, M., Wallraven, C., Fleming, R.W.: Image statistics for clustering paintings according to their visual appearance. In: Deussen, O., et al. (eds.) Computational Aesthetics 2009, 2009, pp. 1–8. Eurographics, Aire-La-Ville (2009)Google Scholar
  20. [TMR02]
    Taubman, D.S., Marcellin, M.W., Rabbani, M.: JPEG2000: Image compression fundamentals, standards and practice. Journal of Electronic Imaging 11, S. 286 (2002)CrossRefGoogle Scholar
  21. [TO99]
    Torralba, A.B., Oliva, A.: Semantic Organization of Scenes Using Discriminant Structural Templates. In: IEEE International Conference on Computer Vision, vol. 2, p. S. 1253 (1999)Google Scholar
  22. [TO03]
    Torralba, A., Oliva, A.: Statistics of natural image categories. Network: Computation in Neural Systems 14(3) (2003)Google Scholar
  23. [Tor11]
    Torralba, Antonio: Spatial Envelope, Version: März 2011, http://people.csail.mit.edu/torralba/code/spatialenvelope/
  24. [TTC92]
    Tolhurst, D.J., Tadmor, Y., Chao, T.: Amplitude spectra of natural images. Ophthalmic Physiol Opt. 12(2), S. 229–S. 232 (1992)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Marcel Spehr
    • 1
  • Stefan Gumhold
    • 1
  • Roland W. Fleming
    • 2
  1. 1.Inst. of Software- and Multimedia-Technology, Computer Graphics and Visualization (CGV) labTechnische Universität DresdenDresdenGermany
  2. 2.Dept. of PsychologyUniversity of GiessenGiessenGermany

Personalised recommendations