Abstract
We present a multiscale nonlinear image representation that permits an efficient coding of natural images. The input image is first decomposed into a set of subbands at multiple scales and orientations using near-orthogonal symmetric quadrature mirror filters. This is followed by a nonlinear “divisive normalization” stage, in which each linear coefficient is divided by a value computed from a small set of neighboring coefficients in space, orientation and scale. This neighborhood is chosen to allow this nonlinear operation to be efficiently inverted. The parameters of the normalization operation are optimized in order to maximize the independence of the normalized responses for natural images. We demonstrate the near-independence of these nonlinear responses, and suggest a number of applications for which this representation should be well suited.
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
Field, D.J.: Relations between the statistics of natural images and the response properties of cortical cells. J. Opt. Soc. Am. A 4(12), 2379–2394 (1987)
Olshausen, B.A., Field, D.J.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381, 607–609 (1996)
Bell, J., Sejnowski, T.J.: The independent components of natural scenes are edge filters. Vision Research 37(23), 3327–3338 (1997)
Wegmann, B., Zetzsche, C.: Statistical dependence between orientation filter outputs used in an human vision based image code. In: Proc. SPIE Vis. Commun. Image Processing, vol. 1360, pp. 909–922 (1990)
Simoncelli, E.P.: Statistical models for images: compression, restoration and synthesis. In: Asilomar Conf. Signals, Systems, Comput., pp. 673–679 (1997)
Simoncelli, E.P., Schwartz, O.: Modeling surround suppression in V1 neurons with a statistically-derived normalization model. Advances in Neural Information Processing Systems 11, 153–159 (1999)
Schwartz, O., Simoncelli, E.P.: Natural signal statistics and sensory gain control. Nature neuroscience 4(8), 819–825 (2001)
Wainwright, M.J., Schwartz, O., Simoncelli, E.P.: Natural image statistics and divisive normalization: modeling nonlinearities and adaptation in cortical neurons. In: Rao, R., Olshausen, B., Lewicki, M. (eds.) Statistical Theories of the Brain. ch. 10, pp. 203–222. MIT Press, Cambridge (2002)
Albrecht, D.G., Geisler, W.S.: Motion sensitivity and the contrast-response function of simple cells in the visual cortex. Visual Neuroscience 7, 531–546 (1991)
Heeger, D.J.: Normalization of cell responses in cat striate cortex. Visual Neuroscience 9, 181–198 (1992)
Foley, J.M.: Human luminance pattern mechanisms: masking experiments require a new model. Journal of the Optical Society of America A 11, 1710–1719 (1994)
Malo, J., Simoncelli, E.P., Epifanio, I., Navarro, R.: Nonlinear image representation for efficient coding (2003) (to be submitted)
Egger, O., Li, W., Kunt, M.: High compression image coding using an adaptive morphological subband decomposition. Proceedings of the IEEE 83, 272–287 (1995)
Hampson, F.J., Pesquet, J.C.: M-band nonlinear subband decompositions with perfect reconstruction. IEEE Transactions on Image Processing 7, 1547–1560 (1998)
de Queiroz, R.L., Florencio, D.A.F., Schafer, R.W.: Nonexpansive pyramid for image coding using a nonlinear filterbank. IEEE Transactions on Image Processing 7, 246–252 (1998)
Salembier, P., Kunt, M.: Size-sensitive multiresolution decompositions of images with rank order based filters. Signal Processing 27, 205–241 (1992)
Bangham, J.A., Campbell, T.G., Aldridge, R.V.: Multiscale median and morphological filters for 2D pattern recognition. Signal Processing 38, 387–415 (1994)
Arce, G.R., Tian, M.: Order statistic filter banks. IEEE Transactions on Image Processing 5, 827–837 (1996)
Egger, O., Li, W.: Very low bit rate image coding using morphological operators and adaptive decompositions. In: Proceedings of the IEEE International Conference on Image Processing, pp. 326–330 (1994)
Egger, O., Fleury, P., Ebrahimi, T., Kunt, M.: High-performance compression of visual information – A tutorial review: I. Still pictures. Proceedings of the IEEE 87, 976–1013 (1999)
Goutsias, J., Heijmans, A.M.: Nonlinear multiresolution signal decomposition schemes - Part II: Morphological wavelets. IEEE Transactions on Image Processing 9, 1862–1913 (2000)
Simoncelli, E.P., Adelson, E.H.: Subband image coding. In: Woods, J.W. (ed.) Subband Transforms. ch. 4, pp. 143–192. Kluwer Academic Publishers, Norwell (1990)
Nestares, O., Navarro, R., Portilla, J., Tabernero, A.: Efficient spatial-domain implementation of a multiscale image representation based on Gabor functions. Journal of Electronic Imaging 7(1), 166–173 (1998)
Wainwright, M.J., Simoncelli, E.P.: Scale mixtures of Gaussians and the statistics of natural images. Advances in Neural Information Processing Systems 12, 855–861 (2000)
Buccigrossi, R.W., Simoncelli, E.P.: Image compression via joint statistical characterization in the wavelet domain. IEEE Transactions on Image Processing 8(12), 1688–1701 (1999)
Malo, J., Ferri, F., Navarro, R., Valerio, R.: Perceptually and statistically decorrelated features for image representation: application to transform coding. In: Proceedings of the 15TH International Conference on Pattern Recognition, vol. 3, pp. 242–245 (2000)
Teo, P., Heeger, D.: Perceptual image distortion. In: Proceedings of the IEEE International Conference on Image Processing, vol. 2, pp. 982–986 (1994)
Watson, B., Solomon, J.A.: Model of visual contrast gain control and pattern masking. Journal of the Optical Society of America A 14(9), 2379–2391 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Valerio, R., Simoncelli, E.P., Navarro, R. (2003). Directly Invertible Nonlinear Divisive Normalization Pyramid for Image Representation. In: García, N., Salgado, L., Martínez, J.M. (eds) Visual Content Processing and Representation. VLBV 2003. Lecture Notes in Computer Science, vol 2849. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39798-4_42
Download citation
DOI: https://doi.org/10.1007/978-3-540-39798-4_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20081-9
Online ISBN: 978-3-540-39798-4
eBook Packages: Springer Book Archive