A NEURAL NETWORK TO COMPUTE THE HUTCHINSON METRIC IN FRACTAL IMAGE-PROCESSING

被引：11

作者：

STARK, J

机构：

[1] Long Range Research Laboratory, GEC-Marconi Ltd., Hirst Research Centre, Middlesex, East Lane. Wembley

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1991年 / 2卷 / 01期

关键词：

D O I：

10.1109/72.80303

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The Hutchinson metric is a natural measure of the discrepancy between two images for use in fractal image processing. We describe a neural network which can quickly calculate this metric. By combining this with the architecture described in [12] for implementing the Markov operator of an iterated function system (IFS) on a neural network, we give a fast method for determining the distance between a target image and the invariant measure of a trial IFS. This has obvious applications to Barnsley's fractal image compression scheme [3]-[6].

引用

页码：156 / 158

页数：3

共 14 条

[1]

Barnsley M. F., 1993, FRACTALS EVERYWHERE, Vsecond

[2]

BARNSLEY MF, 1988, BYTE, V13, P215

[3] ITERATED FUNCTION SYSTEMS AND THE GLOBAL CONSTRUCTION OF FRACTALS [J].