Hidden Markov models for wavelet-based signed processing

Matthew S. Crouse; Richard G. Baraniuk; Robert D. Nowak

Hidden Markov models for wavelet-based signed processing

Matthew S. Crouse, Richard G. Baraniuk, Robert D. Nowak

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Current wavelet-based statistical signal and image processing techniques such as shrinkage and filtering treat the wavelet coefficients as though they were statistically independent. This assumption is unrealistic; considering the statistical dependencies between wavelet coefficients can yield substantial performance improvements. In this paper, we develop a new framework for wavelet-based signal processing that employs hidden Markov models to characterize the dependencies between wavelet coefficients. To illustrate the power of the new framework, we derive a new signal denoising algorithm that outperforms current scalar shrinkage techniques.

Original language	English (US)
Title of host publication	Conference Record of the Asilomar Conference on Signals, Systems and Computers
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1029-1035
Number of pages	7
Volume	2
State	Published - 1997
Event	Proceedings of the 1996 30th Asilomar Conference on Signals, Systems & Computers. Part 2 (of 2) - Pacific Grove, CA, USA Duration: Nov 3 1996 → Nov 6 1996

Other

Other	Proceedings of the 1996 30th Asilomar Conference on Signals, Systems & Computers. Part 2 (of 2)
City	Pacific Grove, CA, USA
Period	11/3/96 → 11/6/96

ASJC Scopus subject areas

Hardware and Architecture
Signal Processing
Electrical and Electronic Engineering

Cite this

Hidden Markov models for wavelet-based signed processing. / Crouse, Matthew S.; Baraniuk, Richard G.; Nowak, Robert D.

Conference Record of the Asilomar Conference on Signals, Systems and Computers. Vol. 2 Institute of Electrical and Electronics Engineers Inc., 1997. p. 1029-1035.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Crouse, MS, Baraniuk, RG & Nowak, RD 1997, Hidden Markov models for wavelet-based signed processing. in Conference Record of the Asilomar Conference on Signals, Systems and Computers. vol. 2, Institute of Electrical and Electronics Engineers Inc., pp. 1029-1035, Proceedings of the 1996 30th Asilomar Conference on Signals, Systems & Computers. Part 2 (of 2), Pacific Grove, CA, USA, 11/3/96.

@inproceedings{52b79c3d9f014c939b398c1156eb251d,

title = "Hidden Markov models for wavelet-based signed processing",

abstract = "Current wavelet-based statistical signal and image processing techniques such as shrinkage and filtering treat the wavelet coefficients as though they were statistically independent. This assumption is unrealistic; considering the statistical dependencies between wavelet coefficients can yield substantial performance improvements. In this paper, we develop a new framework for wavelet-based signal processing that employs hidden Markov models to characterize the dependencies between wavelet coefficients. To illustrate the power of the new framework, we derive a new signal denoising algorithm that outperforms current scalar shrinkage techniques.",

author = "Crouse, {Matthew S.} and Baraniuk, {Richard G.} and Nowak, {Robert D.}",

year = "1997",

language = "English (US)",

volume = "2",

pages = "1029--1035",

booktitle = "Conference Record of the Asilomar Conference on Signals, Systems and Computers",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "Proceedings of the 1996 30th Asilomar Conference on Signals, Systems & Computers. Part 2 (of 2) ; Conference date: 03-11-1996 Through 06-11-1996",

}

TY - GEN

T1 - Hidden Markov models for wavelet-based signed processing

AU - Crouse, Matthew S.

AU - Baraniuk, Richard G.

AU - Nowak, Robert D.

PY - 1997

Y1 - 1997

N2 - Current wavelet-based statistical signal and image processing techniques such as shrinkage and filtering treat the wavelet coefficients as though they were statistically independent. This assumption is unrealistic; considering the statistical dependencies between wavelet coefficients can yield substantial performance improvements. In this paper, we develop a new framework for wavelet-based signal processing that employs hidden Markov models to characterize the dependencies between wavelet coefficients. To illustrate the power of the new framework, we derive a new signal denoising algorithm that outperforms current scalar shrinkage techniques.

AB - Current wavelet-based statistical signal and image processing techniques such as shrinkage and filtering treat the wavelet coefficients as though they were statistically independent. This assumption is unrealistic; considering the statistical dependencies between wavelet coefficients can yield substantial performance improvements. In this paper, we develop a new framework for wavelet-based signal processing that employs hidden Markov models to characterize the dependencies between wavelet coefficients. To illustrate the power of the new framework, we derive a new signal denoising algorithm that outperforms current scalar shrinkage techniques.

UR - http://www.scopus.com/inward/record.url?scp=0030707129&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030707129&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030707129

VL - 2

SP - 1029

EP - 1035

BT - Conference Record of the Asilomar Conference on Signals, Systems and Computers

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - Proceedings of the 1996 30th Asilomar Conference on Signals, Systems & Computers. Part 2 (of 2)

Y2 - 3 November 1996 through 6 November 1996

ER -

Hidden Markov models for wavelet-based signed processing

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this