deposit_your_work

Bayesian Tree-Structured Image Modeling using Wavelet-domain Hidden Markov Models

Files in this item

Files Size Format View
Rom2001Jul1BayesianTr.PDF 312.5Kb application/pdf Thumbnail
Rom2001Jul1BayesianTr.PS 2.223Mb application/postscript View/Open

Show simple item record

Item Metadata

dc.contributor.author Romberg, Justin
Choi, Hyeokho
Baraniuk, Richard G.
dc.creator Romberg, Justin
Choi, Hyeokho
Baraniuk, Richard G.
dc.date.accessioned 2007-10-31T01:02:40Z
dc.date.available 2007-10-31T01:02:40Z
dc.date.issued 2001-07-01
dc.date.submitted 2002-07-10
dc.identifier.uri http://hdl.handle.net/1911/20297
dc.description Journal Paper
dc.description.abstract Wavelet-domain hidden Markov models have proven to be useful tools for statistical signal and image processing. The hidden Markov tree (HMT) model captures the key features of the joint probability density of the wavelet coefficients of real-world data. One potential drawback to the HMT framework is the need for computationally expensive iterative training to fit an HMT model to a given data set (using the Expectation-Maximization algorithm, for example). In this paper, we greatly simplify the HMT model by exploiting the inherent self-similarity of real-world images. This simplified model specifies the HMT parameters with just nine meta-parameters (independent of the size of the image and the number of wavelet scales). We also introduce a Bayesian universal HMT (uHMT) that fixes these nine parameters. The uHMT requires no training of any kind. While extremely simple, we show using a series of image estimation/denoising experiments that these new models retain nearly all of the key image structure modeled by the full HMT. Finally, we propose a fast shift-invariant HMT estimation algorithm that outperforms other wavelet-based estimators in the current literature, both visually and in mean-square error.
dc.description.sponsorship Defense Advanced Research Projects Agency
dc.description.sponsorship Office of Naval Research
dc.description.sponsorship National Science Foundation
dc.language.iso eng
dc.subject hidden markov models
besov space
cycle spinning
image denoising
dc.subject.other Image Processing and Pattern analysis
Wavelet based Signal/Image Processing
Multiscale Methods
dc.title Bayesian Tree-Structured Image Modeling using Wavelet-domain Hidden Markov Models
dc.type Journal Paper
dc.citation.bibtexName article
dc.citation.journalTitle IEEE Transactions on Image Processing
dc.date.modified 2006-06-06
dc.contributor.center Center for Multimedia Communications (http://cmc.rice.edu/)
dc.contributor.center Digital Signal Processing (http://dsp.rice.edu/)
dc.subject.keyword hidden markov models
besov space
cycle spinning
image denoising
dc.citation.volumeNumber 10
dc.citation.pageNumber 1056-1068
dc.citation.issueNumber 7
dc.type.dcmi Text
dc.identifier.citation J. Romberg, H. Choi and R. G. Baraniuk, "Bayesian Tree-Structured Image Modeling using Wavelet-domain Hidden Markov Models," IEEE Transactions on Image Processing, vol. 10, no. 7, pp. 1056-1068, 2001.

This item appears in the following Collection(s)

  • ECE Publications [1032 items]
    Publications by Rice University Electrical and Computer Engineering faculty and graduate students
  • DSP Publications [508 items]
    Publications by Rice Faculty and graduate students in digital signal processing.