An optimization approach to unsupervised hierarchical texture segmentation

Author

Hofmann, T. ; Puzicha, J. ; Buhmann, J.M.

Author_Institution

Center for Biol. & Comput. Learning, MIT, Cambridge, MA, USA

Volume

3

fYear

1997

fDate

26-29 Oct 1997

Firstpage

213

Abstract

We introduce a novel optimization framework for hierarchical data clustering and apply it to the problem of unsupervised texture segmentation. The proposed objective function assesses the quality of an image partitioning simultaneously at different resolution levels and yields a sequence of consistently nested image segmentations. A novel model selection criterion to select significant image structures from various scales is proposed. As an efficient deterministic optimization heuristic a mean-field annealing algorithm is derived

Keywords

deterministic algorithms; image recognition; image resolution; image segmentation; image sequences; image texture; optimisation; unsupervised learning; deterministic optimization heuristic; hierarchical data clustering; image partitioning quality; image sequence; image structures; mean-field annealing algorithm; model selection criterion; nested image segmentations; objective function; optimization approach; resolution levels; scales; unsupervised hierarchical texture segmentation; Annealing; Biology computing; Bismuth; Frequency; Gabor filters; Image resolution; Image segmentation; Optimization methods; Partitioning algorithms; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1997. Proceedings., International Conference on

Conference_Location

Santa Barbara, CA

Print_ISBN

0-8186-8183-7

Type

conf

DOI

10.1109/ICIP.1997.632061

Filename

632061