Bayesian multiresolution map estimation of edge or transition point location in noisy signals

Yegim Serinaijaoglu, Dana H. Brooks, Shien-Fong Lin, T. J. Wu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present a Bayesian scheme for estimation of the location of an extremum of the first or second derivative of a noisy signal in a given interval using a scale-recursive multiresolution approach, as a means to locate edges or transition points. The estimation is carried out on the wavelet coefficients using a coarse-To-fine cross-scale search. A prior is specified for the location of the extremum at a given scale based on a location estimate at a coarser scale and a likelihood function is specified based on a rank-ordered version of the wavelet coefficients, leading to a MAP estimate at the given scale. This then becomes the location parameter for the prior at the next finer scale in a scale-recursive MAP estimation scheme. We include examples using both synthetic signals and optically measured cardiac electrical signals.

Original languageEnglish
Title of host publicationSignal Processing Theory and Methods I
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages628-631
Number of pages4
ISBN (Electronic)0780362934
DOIs
StatePublished - 1 Jan 2000
Event25th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2000 - Istanbul, Turkey
Duration: 5 Jun 20009 Jun 2000

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume1
ISSN (Print)1520-6149

Conference

Conference25th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2000
CountryTurkey
CityIstanbul
Period5/06/009/06/00

Fingerprint Dive into the research topics of 'Bayesian multiresolution map estimation of edge or transition point location in noisy signals'. Together they form a unique fingerprint.

Cite this