Share Email Print

Proceedings Paper

Contextual Analysis Of Ultrasonic B-Mode Images.
Author(s): D. Bensakhria; M. Bertrand; G. Mailloux; R. Stampfier; S. Ethier
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In order to reduce the classification errors when labeling texture pixels, the contextual information can be used to reduce the ambiguity attached to pixel classification. A post-processing approach is introduced whereby the context is modeled according to a Markov-Gibbs assumption to describe the local characteritics of a pixel label. Results of some pathological cases are presented.

Paper Details

Date Published: 10 September 1987
PDF: 8 pages
Proc. SPIE 0768, Pattern Recognition and Acoustical Imaging, (10 September 1987); doi: 10.1117/12.940286
Show Author Affiliations
D. Bensakhria, Ecole Polytechnique de Montreal (Canada)
M. Bertrand, Ecole Polytechnique de Montreal (Canada)
G. Mailloux, Ecole Polytechnique de Montreal (Canada)
R. Stampfier, Ecole Polytechnique de Montreal (Canada)
S. Ethier, Hotel-Dieu Hospital (Canada)

Published in SPIE Proceedings Vol. 0768:
Pattern Recognition and Acoustical Imaging
Leonard A. Ferrari, Editor(s)

© SPIE. Terms of Use
Back to Top