THE STATISTICS OF NATURAL IMAGES

被引：685

作者：

RUDERMAN, DL

机构：

来源：

NETWORK-COMPUTATION IN NEURAL SYSTEMS | 1994年 / 5卷 / 04期

关键词：

D O I：

10.1088/0954-898X/5/4/006

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：517 / 548

页数：32

共 89 条

[1]

[Anonymous], 1966, PHYSICS, DOI DOI 10.1103/PHYSICSPHYSIQUEFIZIKA.2.263

[2]

[Anonymous], 1987, RETINA APPROACHABLE

[3]

[Anonymous], 1991, COMMUNICATIONS SIGNA

[4] COMPARISON OF INTERNATIONAL STANDARDS FOR LOSSLESS STILL IMAGE COMPRESSION [J].