zbMATH — the first resource for mathematics

The two-dimensional Gabor function adapted to natural image statistics: a model of simple-cell receptive fields and sparse structure in images. (English) Zbl 1414.92031
Summary: The two-dimensional Gabor function is adapted to natural image statistics, leading to a tractable probabilistic generative model that can be used to model simple cell receptive field profiles, or generate basis functions for sparse coding applications. Learning is found to be most pronounced in three Gabor function parameters representing the size and spatial frequency of the two-dimensional Gabor function and characterized by a nonuniform probability distribution with heavy tails. All three parameters are found to be strongly correlated, resulting in a basis of multiscale Gabor functions with similar aspect ratios and size-dependent spatial frequencies. A key finding is that the distribution of receptive-field sizes is scale invariant over a wide range of values, so there is no characteristic receptive field size selected by natural image statistics. The Gabor function aspect ratio is found to be approximately conserved by the learning rules and is therefore not well determined by natural image statistics. This allows for three distinct solutions: a basis of Gabor functions with sharp orientation resolution at the expense of spatial-frequency resolution, a basis of Gabor functions with sharp spatial-frequency resolution at the expense of orientation resolution, or a basis with unit aspect ratio. Arbitrary mixtures of all three cases are also possible. Two parameters controlling the shape of the marginal distributions in a probabilistic generative model fully account for all three solutions. The best-performing probabilistic generative model for sparse coding applications is found to be a gaussian copula with Pareto marginal probability density functions.
92B20 Neural networks for/in biological studies, artificial life and related topics
62P10 Applications of statistics to biology and medical sciences; meta analysis
KDE Toolbox
Full Text: DOI
[1] Atteneave, F. (1954). Some informational aspects of visual perception. Psychological Review, 6, 183-193. ,
[2] Barlow, H. B. (1961). Possible principles underlying the transformations of sensory messages. In W. A. Rosenblith (Ed.), Sensory communication (pp. 217-234). Cambridge, MA: MIT Press.
[3] Bell, A. J., & Sejnowski, T. J. (1997). The “independent components” of natural scenes are edge filters. Vision Res., 37, 3327-3338. ,
[4] Bethge, M. (2006). Factorial coding of natural images: How effective are linear models in removing higher-order dependencies? J. Opt. Soc. Am. A, 23, 1253-1268. ,
[5] Bishop, C. M. (2006). Pattern recognition and machine learning. New York: Springer. , · Zbl 1107.68072
[6] Boyd, S., & Vandenberghe, L. (2004). Convex optimization. Cambridge: Cambridge University Press. , · Zbl 1058.90049
[7] Daugman, J. G. (1985). Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J. Opt. Soc. Am. A, 2, 1160-1169. ,
[8] Daugman, J. G. (1988). Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression. IEEE Trans. Acoustics, Speech, Sig. Proc., 36, 1169-1179. , · Zbl 0709.94577
[9] Daugman, J. G. (1989). Entropy reduction and decorrelation in visual coding by oriented neural receptive fields. IEEE Trans. Biomed. Eng., 36, 107-114. ,
[10] Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. J. Royal Stat. Soc. Series B, 39, 1-38. · Zbl 0364.62022
[11] Durbin, R., & Mitchison, G. (1990). A dimension reduction framework for understanding cortical maps. Nature, 343, 644-647. ,
[12] Eichhorn, J., Sinz, F., & Bethge, M. (2009). Natural image coding in V1: How much use is orientation selectivity? PLOS Comp. Biol., 5, e1000336. ,
[13] Embrechts, P., Lindskog, F., & McNeil, A. (2001). Modelling dependence with copulas. In S. T. Rachev (Ed.), Handbook of heavy tailed distributions in finance. Amsterdam: Elsevier Science.
[14] Field, D. J. (1987). Relations between the statistics of natural images and the response properties of cortical cells. J. Opt. Soc. Am. A, 4, 2379-2394. ,
[15] Field, D. J. (1994). What is the goal of sensory coding? Neural Comp., 6, 559-601. ,
[16] Földiák, P. (1990). Forming sparse representations by local anti-Hebbian learning. Biol. Cybern., 64, 165-170. ,
[17] Hosseini, R., Sinz, F., & Bethge, M. (2010). Lower bounds on the redundancy of natural images. J. Vision Res., 50, 2213-2222. ,
[18] Hubel, D. H., & Wiesel, T. N. (1959). Receptive fields of single neurones in the cat’s striate cortex. J. Physiol., 148, 574-591. ,
[19] Hubel, D. H., & Wiesel, T. N. (1962). Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J. Physiol., 160, 105-154. ,
[20] Hyvärinen, A., & Hoyer, P. (2000). Emergence of phase- and shift-invariant features by decomposition of natural images into independent feature subspaces. Neural Comput., 12, 1705-1720. ,
[21] Hyvärinen, A., Hoyer, P., & Inki, M. (2001). Topographic independent component analysis. Neural Comput., 13, 1527-1558. , · Zbl 1009.62049
[22] Hyvärinen, A., Hurri, J., & Hoyer, P. O. (2009). Natural image statistics. London: Springer-Verlag. , · Zbl 1178.68622
[23] Ihler, A. (2003). Kernel density estimation toolbox for Matlab.
[24] Jones, J. P., & Palmer, L. A. (1987). An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. J. Neurophys., 58, 1233-1258.
[25] Lee, T. S. (1996). Image representation using 2D Gabor wavelets. IEEE Trans. Pattern. Anal. Mach. Intell., 18, 959-971. ,
[26] Lewicki, M. S., & Olshausen, B. A. (1999). Probabilistic framework for the adaptation and comparison of image codes. J. Opt. Soc. Am. A, 16, 1587-1601. ,
[27] Li, Z., & Atick, J. J. (1994). Towards a theory of striate cortex. Neural Comput., 6, 127-146. ,
[28] Linsker, R. (1986). From basic network principles to neural architecture: Emergence of orientation selective cells. Proc. Natl. Acad. Sci. USA, 83, 8390-8394. ,
[29] Loxley, P. N. (2017). Matlab code for the PPCA-copula generative model downloadable from
[30] Marcelja, S. (1980). Mathematical description of the responses of simple cortical cells. J. Opt. Soc. Am., 70, 1297-1300. ,
[31] Mumford, D., & Gidas, B. (2001). Stochastic models for generic images. Quarterly Appl. Math., 59, 85-111. , · Zbl 1159.68598
[32] Olmos, A., & Kingdom, F. A. A. (2004). A biologically inspired algorithm for the recovery of shading and reflectance images. Perception, 33, 1463-1473. ,
[33] Olshausen, B. A. (2013). Highly overcomplete sparse coding. In Proc. SPIE 8651, Human Vision and Electronic Imaging XVIII. New York: Springer. doi: 10.1117/12.2013504. ,
[34] Olshausen, B. A., & Field, D. J. (1996). Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381, 607-609. ,
[35] Olshausen, B. A., & Field, D. J. (1997). Sparse coding with an overcomplete basis set: A strategy employed by V1? Vision Res., 37, 3311-3325. ,
[36] Petrov, Y., & Li, Z. (2003). Local correlations, information redundancy, and sufficient pixel depth in natural images. J. Opt. Soc. Am. A, 20, 56-66. ,
[37] Rehn, M., & Sommer, T. (2007). A network that uses few active neurones to code visual input predicts the diverse shapes of cortical receptive fields. J. Comput. Neurosci., 22, 135-146. ,
[38] Ringach, D. L. (2002). Spatial structure and symmetry of simple-cell receptive fields in macaque primary visual cortex. J. Neurophysiol., 88, 455-463.
[39] Ruderman, D. L. (1997). Origins of scaling in natural images. Vision Res., 37, 3385-3398. ,
[40] Ruderman, D. L., & Bialek, W. (1994). Statistics of natural images: Scaling in the woods. Phys. Rev. Lett., 73, 814-817. ,
[41] Seeger, M. W. (2008). Bayesian inference and optimal design for the sparse linear model. J. Machine Learning Res., 9, 759-813. · Zbl 1225.68213
[42] Swindale, N. V. (1996). The development of topography in the visual cortex. Network: Comp. in Neural Syst., 7, 161-247. , · Zbl 0903.92012
[43] Tipping, M. E., & Bishop, C. M. (1999). Probabilistic principal component analysis. J. Royal Stat. Soc. Series B, 21, 611-622. , · Zbl 0924.62068
[44] van Hateren, J. H., & van der Schaaf, A. (1998). Independent component filters of natural images compared with simple cells in primary visual cortex. Proc. R. Soc. Lond. B, 265, 359-366. ,
[45] von der Malsburg, Ch. (1973). Self-organization of orientation sensitive cells in the striate cortex. Kybernetik, 14, 85-100. ,
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.