Minimax Entropy Principle and Its Application to Texture Modeling

Minimax Entropy Principle and Its Application to Texture Modeling (1997)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Song Chun Zhu , Ying Nian Wu , David Mumford

Citations:

165 - 33 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Minimax Entropy Principle and Its Application to Texture Modeling	SVM HeaderParse 0.1
AUTHOR NAME	Song Chun	SVM HeaderParse 0.1
AUTHOR AFFIL	Division of Applied Mathematics, Brown University, Providence	SVM HeaderParse 0.2
AUTHOR ADDR	RI 02912	SVM HeaderParse 0.1
AUTHOR NAME	Zhu Nian	SVM HeaderParse 0.1
AUTHOR NAME	Wu David Mumford	SVM HeaderParse 0.1
AUTHOR AFFIL	Department of Statistics, Harvard University, Cambridge	SVM HeaderParse 0.2
AUTHOR ADDR	MA 02138.	SVM HeaderParse 0.1
ABSTRACT	This article proposes a general theory and methodology, called the minimax entropy principle, for building statistical models for images (or signals) in a variety of applications. This principle consists of two parts. The first is the maximum entropy principle for feature binding (or fusion): for a certain set of feature statistics, a distribution can be built to bind these feature statistics together by maximizing the entropy over all distributions that reproduce these feature statistics. The second part is the minimum entropy principle for feature selection: among all plausible sets of feature statistics, we choose the set whose maximum entropy distribution has the minimum entropy. Computational and inferential issues in both parts are addressed, in particular, a feature pursuit procedure is proposed for approximately selecting the optimal set of features. The model complexity is restricted because of the sample variation in the observed feature statistics. The minimax entropy principle is applied to texture modeling, where a novel Markov random field (MRF) model, called FRAME (Filter, Random field, And Minimax Entropy), is derived, and encouraging results are obtained in experiments on a variety of texture images. Relationship between our theory and the mechanisms of neural computation is also discussed.	SVM HeaderParse 0.1
CITATIONS	38 found	ParsCit 1.0