Share Email Print

Proceedings Paper

A learned distance function for medical image similarity retrieval
Author(s): Dave Tahmoush
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

One fundamental problem remains in the area of image analysis and retrieval: how to measure perceptual similarity between two images. Most researchers employ a Minkowski-type metric, which does not reliably find similarities in objects that are obviously alike. This paper develops a similarity function that is learned in order to capture the perception of similarity. The technique first extracts high-level landmarks in the images to determine a local contextual similarity, but these are unordered and unregistered. Second, the point sets of the two images are fed into the learned similarity function to determine the overall similarity. This technique avoids arbitrary spatial constraints and is robust in the presence of noise, outliers, and imaging artifacts.

Paper Details

Date Published: 13 March 2009
PDF: 8 pages
Proc. SPIE 7264, Medical Imaging 2009: Advanced PACS-based Imaging Informatics and Therapeutic Applications, 726406 (13 March 2009); doi: 10.1117/12.811365
Show Author Affiliations
Dave Tahmoush, Univ. of Maryland, College Park (United States)
U.S. Army Research Lab. (United States)

Published in SPIE Proceedings Vol. 7264:
Medical Imaging 2009: Advanced PACS-based Imaging Informatics and Therapeutic Applications
Khan M. Siddiqui M.D.; Brent J. Liu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?