The statistics of natural images
- 1 November 1994
- journal article
- research article
- Published by Taylor & Francis in Network: Computation in Neural Systems
- Vol. 5 (4) , 517-548
- https://doi.org/10.1088/0954-898x/5/4/006
Abstract
Recently there has been a resurgence of interest in the properties of natural images. Their statistics are important not only in image compression but also for the study of sensory processing in biology, which can be viewed as satisfying certain ‘design criteria’. This review summarizes previous work on image statistics and presents our own data. Perhaps the most notable property of natural images is an invariance to scale. We present data to support this claim as well as evidence for a hierarchical invariance in natural scenes. These symmetries provide a powerful description of natural images as they greatly restrict the class of allowed distributions.This publication has 62 references indexed in Scilit:
- Entropy and Long-Range Correlations in Literary EnglishEurophysics Letters, 1994
- Toward a Theory of the Striate CortexNeural Computation, 1994
- Coding Efficiency and Information Rates in Sensory NeuronsEurophysics Letters, 1993
- Normalization of cell responses in cat striate cortexVisual Neuroscience, 1992
- Spectral reflectance of natural objects: how many basis functions are necessary?Journal of the Optical Society of America A, 1992
- Compound Gauss-Markov random fields for image estimationIEEE Transactions on Signal Processing, 1991
- Towards a Theory of Early Visual ProcessingNeural Computation, 1990
- Group invariant pattern recognitionPattern Recognition, 1990
- Fractal structures in turbulenceJournal of Statistical Physics, 1984
- The renormalization group and critical phenomenaReviews of Modern Physics, 1983