Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

DAAL019620001 Image Segmentation and Labeling

Summary: CAR­TR­860
May 1997
Image Segmentation and Labeling
Using the Polya Urn Model
Amit Banerjeey Philippe Burlinay Fady Alajajiz
yCenter for Automation Research
University of Maryland at College Park
College Park, MD 20742­3275
zDepartment of Mathematics and Engineering
Queen's University
Kingston, ON K7L 3N6, Canada
We propose a segmentation method based on Polya's urn model for contagious phenomena.
An initial estimate of the pixel labels is obtained using a Maximum Likelihood (ML) estimate
or the Nearest Mean Classifier (NMC), which are used to determine the initial composition
of an urn representing the pixel. The resulting urns are then subjected to a modified urn
sampling scheme mimicking the development of an infection to yield a segmentation of the
image into homogeneous regions. This process is implemented using contagion urn processes


Source: Alajaji, Fady - Department of Mathematics and Statistics, Queen's University (Kingston)


Collections: Engineering