Help Privacy Policy Disclaimer
  Advanced SearchBrowse





Classification of Natural Scenes using Global Image Statistics


Wichmann,  FA
Max Planck Institute for Biological Cybernetics, Max Planck Society;
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available

Drewes, J., Wichmann, F., & Gegenfurtner, K. (2005). Classification of Natural Scenes using Global Image Statistics. Poster presented at 8th Tübinger Wahrnehmungskonferenz (TWK 2005), Tübingen, Germany.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0013-D637-7
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 nonanimal
images. After applying a DFT to the image, we put the Fourier spectrum of each image
into 48 bins (8 orientations with 6 frequency bands). Using all of these bins, classification
performance on the Fourier spectrum reached 70. In an iterative procedure, we then removed
the bins whose absence caused the smallest damage to the classification performance (one
bin per iteration). Notably, performance stayed at about 70 until less then 6 bins were left.
A detailed analysis of the classification weights showed that a comparatively high level of
performance (67) could also be obtained when only 2 bins were used, namely the vertical
orientations at the highest spatial frequency band. When using only a single frequency band
(8 bins) we found that 67 classification performance could be reached when only the high
spatial frequency information was used, which 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 pre-filtered images.
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).