Multispectral random field models for synthesis and analysis of color images

被引：32

作者：

Bennett, J ^{[1
]}

Khotanzad, A ^{[1
]}

机构：

[1] So Methodist Univ, Dept Elect Engn, Dallas, TX 75275 USA

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1998年 / 20卷 / 03期

关键词：

color texture models; color texture synthesis; color texture analysis; multispectral random fields; multispectral simultaneous autoregressive models; multispectral Markov random field models; multispectral pseudo-Markov random field models; least squares estimation;

D O I：

10.1109/34.667889

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, multispectral extensions to the traditional gray level simultaneous autoregressive (SAR) and Markov random field (MRF) models are considered. Furthermore, a new image model is proposed, the pseudo-Markov model, which retains the characteristics of the multispectral Markov model, yet admits to a simplified parameter estimation method. These models are well-suited to analysis and modeling of color images. For each model considered, procedures are developed for parameter estimation and image synthesis. Experimental results, based on known image models and natural texture samples, substantiate the validity of these results.

引用

页码：327 / 332

页数：6