Cluster-based probability model and its application to image and texture processing

Author

Popat, Kris ; Picard, Rosalind W.

Author_Institution

Media Lab., MIT, Cambridge, MA, USA

Volume

6

Issue

2

fYear

1997

fDate

2/1/1997 12:00:00 AM

Firstpage

268

Lastpage

284

Abstract

We develop, analyze, and apply a specific form of mixture modeling for density estimation within the context of image and texture processing. The technique captures much of the higher order, nonlinear statistical relationships present among vector elements by combining aspects of kernel estimation and cluster analysis. Experimental results are presented in the following applications: image restoration, image and texture compression, and texture classification

Keywords

data compression; higher order statistics; image classification; image coding; image restoration; image texture; parameter estimation; probability; cluster analysis; cluster-based probability model; density estimation; higher order nonlinear statistical relationships; image compression; image processing; image restoration; kernel estimation; mixture modeling; texture classification; texture compression; texture processing; vector elements; Context modeling; Extraterrestrial phenomena; Image analysis; Image coding; Image restoration; Image texture analysis; Kernel; Probability distribution; Signal processing; Tail;

fLanguage

English

Journal_Title

Image Processing, IEEE Transactions on

Publisher

ieee

ISSN

1057-7149

Type

jour

DOI

10.1109/83.551697

Filename

551697