September 2005
Volume 5, Issue 8
Vision Sciences Society Annual Meeting Abstract  |   September 2005
Classification of natural scenes using global image statistics
Author Affiliations
  • Jan Drewes
    Dept. of Psychology, Giessen University, Giessen, Germany
  • Felix Wichmann
    Max Planck Institute for Biological Cybernetics, Tübingen, Germany
  • Karl R. Gegenfurtner
    Dept. of Psychology, Giessen University, Giessen, Germany
Journal of Vision September 2005, Vol.5, 602. doi:
  • Views
  • Share
  • Tools
    • Alerts
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Jan Drewes, Felix Wichmann, Karl R. Gegenfurtner; Classification of natural scenes using global image statistics. Journal of Vision 2005;5(8):602.

      Download citation file:

      © ARVO (1962-2015); The Authors (2016-present)

  • Supplements

The algorithmic classification of complex, natural scenes is generally considered a difficult task due to the large amount of information conveyed by natural images. Work by Simon Thorpe and colleagues showed that humans are capable of detecting animals within novel natural scenes with remarkable speed and accuracy. This suggests that the relevant information for classification can be extracted at comparatively limited computational cost. One hypothesis is that global image statistics such as the amplitude spectrum could underly fast image classification (Johnson & Olshausen, Journal of Vision, 2003; Torralba & Oliva, Network: Comput. Neural Syst., 2003).

We used linear discriminant analysis to classify a set of 11.000 images into animal and non-animal images. After applying a DFT to the image, we put the Fourier spectrum into bins (8 orientations with 6 frequency bands each). Using all bins, classification performance on the Fourier spectrum reached 70%. However, performance was similar (67%) when only the high spatial frequency information was used and decreased steadily at lower spatial frequencies, reaching a minimum (50%) for the low spatial frequency information. Similar results were obtained when all bins were used on spatially filtered images. A detailed analysis of the classification weights showed that a relatively high level of performance (67%) could also be obtained when only 2 bins were used, namely the vertical and horizontal orientation at the highest spatial frequency band.

Our results show that in the absence of sophisticated machine learning techniques, animal detection in natural scenes is limited to rather modest levels of performance, far below those of human observers. If limiting oneself to global image statistics such as the DFT then mostly information at the highest spatial frequencies is useful for the task. This is analogous to the results obtained with human observers on filtered images (Kirchner et al, VSS 2004).

Drewes, J. Wichmann, F. Gegenfurtner, K. R. (2005). Classification of natural scenes using global image statistics [Abstract]. Journal of Vision, 5(8):602, 602a,, doi:10.1167/5.8.602. [CrossRef]

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.