Unsupervised texture segmentation using a statistical wavelet-based hierarchical multidata model

Author

Destrempes, F. ; Mignotte, M.

Author_Institution

DIRO, Montreal, Que., Canada

Volume

2

fYear

2003

fDate

14-17 Sept. 2003

Abstract

In this paper, we describe a new hidden Markov random field model, which we call hierarchical multidata model, and which is based on a triplet of random fields (two hidden random fields and one observed field) in order to capture interscale and within-scale dependencies between various scales of resolution of wavelet-based texture features. We present a variation of the iterated conditional modes (ICM) algorithm for the segmentation, and an adaptation of the iterative conditional estimation (ICE) procedure for the estimation of the statistical parameters of the model. Results of tests performed on 75 mosaics of Brodatz textures are reported.

Keywords

hidden Markov models; image segmentation; image texture; iterative methods; parameter estimation; wavelet transforms; Brodatz textures; hidden Markov random field model; hierarchical multidata model; iterated conditional modes; iterative conditional estimation; statistical wavelet-based model; unsupervised texture segmentation; Context modeling; Convergence; Data models; Electronic mail; Hidden Markov models; Ice; Iterative algorithms; Performance evaluation; Testing; Wavelet coefficients;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on

ISSN

1522-4880

Print_ISBN

0-7803-7750-8

Type

conf

DOI

10.1109/ICIP.2003.1246866

Filename

1246866