Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Volume

1

fYear

2004

fDate

June 27 2004-July 2 2004

Abstract

The following topics are dealt with: image restoration of curved document images; image segmentation based stereo matching sequence using graph cuts; wavelet based hierarchial surface approximation using local feature subset selection; similarity measure and learning with Gray level aura matrices (GLAM) for texture image retrieval; 3D geometry models coding and morphing for efficient video compression; robust colour object detection using joint probability functions; generalized hidden Markov model; skew Gabor filter in source signal separation and local spectral analysis; motion estimation with optimization; Gibbs maximum likelihood estimation.

Keywords

approximation theory; computational geometry; computer vision; document image processing; filtering theory; graph theory; hidden Markov models; image colour analysis; image matching; image restoration; image retrieval; image segmentation; image sequences; image texture; maximum likelihood estimation; motion estimation; object detection; optimisation; probability; set theory; source separation; spectral analysis; stereo image processing; video coding; wavelet transforms; 3D geometry models; Gabor filter; Gibbs maximum likelihood estimation; Gray level aura matrices; computer vision; curved document images; graph theory; hidden Markov model; image coding; image restoration; image segmentation; local feature subset selection; motion estimation; optimization; pattern recognition; probability; robust colour object detection; source signal separation; spectral analysis; stereo matching sequence; surface approximation theory; texture image retrieval; video compression; wavelet transform;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on

Conference_Location

Washington, DC, USA

ISSN

1063-6919

Print_ISBN

0-7695-2158-4

Type

conf

DOI

10.1109/CVPR.2004.1314997

Filename

1314997