Format

Send to

Choose Destination
See comment in PubMed Commons below
Network. 1996 May;7(2):333-9.

Natural image statistics and efficient coding.

Author information

1
Department of Psychology, Uris Hall, Cornell University, Ithaca, NY 14853, USA. bruno@ai.mit.edu

Abstract

Natural images contain characteristic statistical regularities that set them apart from purely random images. Understanding what these regularities are can enable natural images to be coded more efficiently. In this paper, we describe some of the forms of structure that are contained in natural images, and we show how these are related to the response properties of neurons at early stages of the visual system. Many of the important forms of structure require higher-order (i.e. more than linear, pairwise) statistics to characterize, which makes models based on linear Hebbian learning, or principal components analysis, inappropriate for finding efficient codes for natural images. We suggest that a good objective for an efficient coding of natural scenes is to maximize the sparseness of the representation, and we show that a network that learns sparse codes of natural scenes succeeds in developing localized, oriented, bandpass receptive fields similar to those in the mammalian striate cortex.

PMID:
16754394
DOI:
10.1088/0954-898X/7/2/014
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Taylor & Francis
    Loading ...
    Support Center