Title
Image Segmentation For Automatic Particle Identification In Electron Micrographs Based On Hidden Markov Random Field Models And Expectation Maximization
Abstract
Three-dimensional reconstruction of large macromolecules like viruses at resolutions below 10Å requires a large set of projection images. Several automatic and semi-automatic particle detection algorithms have been developed along the years. Here we present a general technique designed to automatically identify the projection images of particles. The method is based on Markov random field modelling of the projected images and involves a pre-processing of electron micrographs followed by image segmentation and post-processing. The image is modelled as a coupling of two fields - a Markovian and a non-Markovian. The Markovian field represents the segmented image. The micrograph is the non-Markovian field. The image segmentation step involves an estimation of coupling parameters and the maximum á posteriori estimate of the realization of the Markovian field i.e, segmented image. Unlike most current methods, no bootstrapping with an initial selection of particles is required. © 2003 Elsevier Inc. All rights reserved.
Publication Date
1-1-2004
Publication Title
Journal of Structural Biology
Volume
145
Issue
1-2
Number of Pages
123-141
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1016/j.jsb.2003.11.028
Copyright Status
Unknown
Socpus ID
0347985832 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/0347985832
STARS Citation
Singh, Vivek; Marinescu, Dan C.; and Baker, Timothy S., "Image Segmentation For Automatic Particle Identification In Electron Micrographs Based On Hidden Markov Random Field Models And Expectation Maximization" (2004). Scopus Export 2000s. 5774.
https://stars.library.ucf.edu/scopus2000/5774