Information Scaling Laws in Natural Scenes

In natural scenes, objects and patterns can appear at a wide variety of distances from the viewer. For the same visual pattern viewed at different distances, both the image and our perception of the pattern change over distance. We call the change of the image over distance as image scaling, and the change of our perception over distance as information scaling. While image scaling can be accounted for by the state space theory, information scaling has not been mathematically studied in computer vision. In this paper, we prove two information scaling laws: 1) the entropy rate of the image changes over distance, and 2) the entropy of the posterior distribution of the pattern also changes over distance. These two information scaling laws have deep implications in computer vision: they call for different models of the same visual pattern at different distances, as well as a model transition mechanism for switching models over different distance/scale regimes.

[1]  D. Mumford,et al.  Stochastic models for generic images , 2001 .

[2]  Song-Chun Zhu,et al.  Minimax Entropy Principle and Its Application to Texture Modeling , 1997, Neural Computation.

[3]  B. Mandelbrot.  Fractal Geometry of Nature , 1984 .

[4]  David Mumford,et al.  Occlusion Models for Natural Images: A Statistical Study of a Scale-Invariant Dead Leaves Model , 2004, International Journal of Computer Vision.

[5]  Arthur E. C. Pece,et al.  The Problem of Sparse Image Coding , 2002, Journal of Mathematical Imaging and Vision.

[6]  Song-Chun Zhu,et al.  Equivalence of Julesz and Gibbs texture ensembles , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[7]  Song-Chun Zhu,et al.  Towards a mathematical theory of primal sketch and sketchability , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[8]  P Perona,et al.  Preattentive texture discrimination with early vision mechanisms. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[9]  Eero P. Simoncelli,et al.  Natural image statistics and neural representation. , 2001, Annual review of neuroscience.

[10]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[11]  Eero P. Simoncelli,et al.  A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients , 2000, International Journal of Computer Vision.

[12]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  William Bialek,et al.  Statistics of Natural Images: Scaling in the Woods , 1993, NIPS.

[14]  T. Lindeberg,et al.  Scale-Space Theory : A Basic Tool for Analysing Structures at Different Scales , 1994 .

[15]  James R. Bergen,et al.  Pyramid-based texture analysis/synthesis , 1995, Proceedings., International Conference on Image Processing.