Abstract
We investigated ensembles of artificial and real-world grey-scale images to find different invariance properties: translation invariance, scale invariance and a new hierarchical invariance recently proposed by Ruderman [1]. We found that the assumption of translational invariance can be taken for granted. Our results concerning the scale invariance are qualitatively the same as those found by Ruderman [1] and others. The deviations of the distributions of the logarithmically transformed images from a Gaussian distribution cannot be seen as clearly as stated by Ruderman [1]. Depending on the preprocessing of the images the results concerning the hierarchical invariance differed widely. It seems that this new invariance can be confirmed only for logarithmically transformed images.
Preview
Unable to display preview. Download preview PDF.
References
Ruderman, D. L.: The statistics of natural images Network 5 (1994) 517–548
Ruderman, D. L.: Designing receptive fields for highest fidelity Network 5 (1994) 147–155
Field, D. J.: Relations between the statistics of natural images and the response properties of cortical cells J. Opt. Soc. Am. 4 (1987) 2379–2394
Field, D. J.: What is the goal of sensory coding? Neural Comput. 6 (1994) 559–601
Kadanoff, L. P.: Scaling laws for ising models near T c Physics 2 (1966) 263–273
Gardiner, C. W.: Handbook of Stochastic Methods (Berlin, Heidelberg: Springer) 1983
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ziegaus, C., Lang, E.W. (1997). Statistics of natural and urban images. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020159
Download citation
DOI: https://doi.org/10.1007/BFb0020159
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive