An information-theoretic approach to interactions in images

被引：5

作者：

Boccignone, G

Ferraro, M

机构：

[1] Univ Turin, Dipartimento Fis Sperimentale, I-10125 Turin, Italy

[2] INFM, Unita Torino, I-10125 Turin, Italy

[3] Univ Salerno, Dipartimento Ingn Informaz & Ingn Elettr, I-84084 Fisciano, SA, Italy

[4] INFM, Unita Torino, I-84084 Fisciano, SA, Italy

来源：

SPATIAL VISION | 1999年 / 12卷 / 03期

关键词：

D O I：

10.1163/156856899X00201

中图分类号：

Q6 [生物物理学];

学科分类号：

071011 ;

摘要：

In this paper it will be argued that the notion of interactions in images is closely related to that of entropy associated with an image, and it will be shown that interactions make processing of the information coming from the retina computationally less expensive. A procedure will be presented, based on the evolution of joint entropy across different scales, to gauge the contributions of different types of interactions to the structure of the images.

引用

页码：345 / 362

页数：18

共 32 条

[21] NONLINEAR IMAGE FILTERING WITH EDGE AND CORNER ENHANCEMENT [J].