Applications of entropic spanning graphs

Author

Hero, Alfred O., III ; Ma, Bing ; Michel, Olivier J J ; Gorman, John

Volume

19

Issue

5

fYear

2002

fDate

9/1/2002 12:00:00 AM

Firstpage

85

Lastpage

95

Abstract

This article presents applications of entropic spanning graphs to imaging and feature clustering applications. Entropic spanning graphs span a set of feature vectors in such a way that the normalized spanning length of the graph converges to the entropy of the feature distribution as the number of random feature vectors increases. This property makes these graphs naturally suited to applications where entropy and information divergence are used as discriminants: texture classification, feature clustering, image indexing, and image registration. Among other areas, these problems arise in geographical information systems, digital libraries, medical information processing, video indexing, multisensor fusion, and content-based retrieval.

Keywords

entropy; feature extraction; graph theory; image classification; image registration; image texture; indexing; pattern clustering; content-based retrieval; digital libraries; entropic spanning graphs; entropy; feature clustering; feature vectors; geographical information systems; image indexing; image registration; imaging; information divergence; medical information processing; multisensor fusion; normalized spanning length; random feature vectors; texture classification; video indexing; Biomedical imaging; Content based retrieval; Entropy; Image converters; Image registration; Indexing; Information processing; Information retrieval; Information systems; Software libraries;

fLanguage

English

Journal_Title

Signal Processing Magazine, IEEE

Publisher

ieee

ISSN

1053-5888

Type

jour

DOI

10.1109/MSP.2002.1028355

Filename

1028355