Share Email Print
cover

Proceedings Paper

MAP segmentation of magnetic resonance images using mean field annealing
Author(s): Ambalavaner Logenthiran; Wesley E. Snyder; Peter Santago; Kerry M. Link
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

An algorithm is described which segments magnetic resonance images while removing the noise from the images without blurring or other distortion of edges. The problem of segmentation and noise removal is posed as a restoration of an uncorrupted image, given additive white Gaussian noise and a segmentation cost. The problem is solved using a strategy called Mean Field Annealing. An a priori statistical model of the image, which includes the region classification, is chosen which drives the minimization toward solutions which are locally homogeneous and globally classified. Application of the algorithm to brain and knee images is presented.

Paper Details

Date Published: 1 June 1991
PDF: 19 pages
Proc. SPIE 1452, Image Processing Algorithms and Techniques II, (1 June 1991); doi: 10.1117/12.45386
Show Author Affiliations
Ambalavaner Logenthiran, AT&T Bell Labs. (United States)
Wesley E. Snyder, Bowman Gray School of Medicine/Wake Forest Univ. (United States)
Peter Santago, Bowman Gray School of Medicine/Wake Forest Univ. (United States)
Kerry M. Link, Bowman Gray School of Medicine/Wake Forest Univ. (United States)


Published in SPIE Proceedings Vol. 1452:
Image Processing Algorithms and Techniques II
Mehmet Reha Civanlar; Sanjit K. Mitra; Robert J. Moorhead, Editor(s)

© SPIE. Terms of Use
Back to Top