An Automated Volumetric Segmentation System Combining Multiscale and Statistical Reasoning

David W.G. Montgomery, Abbes Amira, Fionn Murtagh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

An automated volumetric image segmentation algorithm is proposed. This method is fast and unsupervised, automatically estimating required parameters including optimal segment number selection using Bayesian inference. In the wavelet domain, Gaussian Mixture Modeling (GMM) is used to achieve a baseline scene estimate. This estimate is then refined to consider spatial correlations using a Markov Random Field Model (MRFM). The application of this system to three-dimensional biomedical image volumes is discussed. This approach delivers promising results in terms of the identification of inherent image features.

Original languageEnglish
Title of host publicationIEEE International Symposium on Circuits and Systems (ISCAS 2005)
PublisherIEEE
Pages3789-3792
Number of pages4
ISBN (Print)0780388348, 9780780388345
DOIs
Publication statusPublished - 25 Jul 2005
Externally publishedYes
EventIEEE International Symposium on Circuits and Systems 2005 - International Conference Center Kobe & Kobe Portopia Hotel, Kobe, Japan
Duration: 23 May 200526 May 2005
https://ieeexplore.ieee.org/document/1407961

Publication series

NameIEEE International Symposium on Circuits and Systems
PublisherIEEE
ISSN (Print)0271-4310
ISSN (Electronic)2158-1525

Conference

ConferenceIEEE International Symposium on Circuits and Systems 2005
Abbreviated titleISCAS 2005
CountryJapan
CityKobe
Period23/05/0526/05/05
Internet address

    Fingerprint

Cite this

Montgomery, D. W. G., Amira, A., & Murtagh, F. (2005). An Automated Volumetric Segmentation System Combining Multiscale and Statistical Reasoning. In IEEE International Symposium on Circuits and Systems (ISCAS 2005) (pp. 3789-3792). (IEEE International Symposium on Circuits and Systems). IEEE. https://doi.org/10.1109/ISCAS.2005.1465455