Abstract
Independent component analysis (ICA), which is equivalent to linear sparse coding, has been recently used as a model of natural image statistics and V1 receptive fields. Olshausen and Field applied the principle of maximizing the sparseness of the coefficients of a linear representation to extract features from natural images. This leads to the emergence of oriented linear filters that have simultaneous localization in space and in frequency, thus resembling Gabor functions and V1 simple cell receptive fields. In this paper, we extend this model to explain emergence of V1 topography. This is done by ordering the basis vectors so that vectors with strong higher-order correlations are near to each other. This is a new principle of topographic organization, and may be more relevant to natural image statistics than the more conventional topographic ordering based on Euclidean distances. For example, this topographic ordering leads to simultaneous emergence of complex cell properties: neighbourhoods act like complex cells.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
A.J. Bell and T.J. Sejnowski. The ‘independent components’ of natural scenes are edge filters. Vision Research, 37:3327–3338, 1997.
J.-F. Cardoso. Multidimensional independent component analysis. In Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP’98), Seattle, WA, 1998.
P. Comon. Independent component analysis — a new concept? Signal Processing, 36:287–314, 1994.
G. C. DeAngelis, G. M. Ghose, I. Ohzawa, and R. D. Freeman. Functional microorganization of primary visual cortex: Receptive field analysis of nearby neurons. Journal of Neuroscience, 19(10):4046–4064, 1999.
G. J. Goodhill and T. J. Sejnowski. A unifying objective function for topographic mappings. Neural Computation, 9(6):1291–1303, 1997.
A. Hyvärinen. Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. on Neural Networks, 10(3):626–634, 1999.
A. Hyvärinen and P. O. Hoyer. Topographic independent component analysis. 1999. Submitted, available at http://www.cis.hut.fi/~aapo/.
A. Hyvärinen and P. O. Hoyer. Emergence of phase and shift invariant features by decomposition of natural images into independent feature subspaces. Neural Computation, 2000. (in press).
A. Hyvärinen and E. Oja. A fast fixed-point algorithm for independent component analysis. Neural Computation, 9(7):1483–1492, 1997.
T. Kohonen. Self-Organizing Maps. Springer-Verlag, Berlin, Heidelberg, New York, 1995.
J. K. Lin. Factorizing multivariate function classes. In Advances in Neural Information Processing Systems, volume 10, pages 563–569. The MIT Press, 1998.
B. A. Olshausen and D. J. Field. Natural image statistics and efficient coding. Network, 7(2):333–340, May 1996.
E. P. Simoncelli and O. Schwartz. Modeling surround suppression in V1 neurons with a statistically-derived normalization model. In Advances in Neural Information Processing Systems 11, pages 153–159. MIT Press, 1999.
N. V. Swindale. The development of topography in the visual cortex: a review of models. Network, 7(2):161–247, 1996.
J. H. van Hateren and A. van der Schaaf. Independent component filters of natural images compared with simple cells in primary visual cortex. Proc. Royal Society ser. B, 265:359–366, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hyvärinen, A., Hoyer, P.O., Inki, M. (2000). Topographic ICA as a Model of Natural Image Statistics. In: Lee, SW., Bülthoff, H.H., Poggio, T. (eds) Biologically Motivated Computer Vision. BMCV 2000. Lecture Notes in Computer Science, vol 1811. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45482-9_54
Download citation
DOI: https://doi.org/10.1007/3-540-45482-9_54
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67560-0
Online ISBN: 978-3-540-45482-3
eBook Packages: Springer Book Archive