Paper Info
Title
A generalized family of fixed-radius distribution-based distance measures for content-based fMRI image retrieval
Abstract
We present a family of distance measures for comparing activation patterns captured in fMRI images. We model an fMRI image as a spatial object with varying density, and measure the distance between two fMRI images using a novel fixed-radius, distribution-based Earth Mover's Distance that is computable in polynomial time. We also present two simplified formulations for the distance computation whose complexity is better than linear programming. The algorithms are robust in the presence of noise, and by varying the radius of the distance measures, can tolerate different degrees of within-class deformation. Empirical evaluation of the algorithms on a dataset of 430 fMRI images in a content-based image retrieval application demonstrates the power and robustness of the distance measures.
Year
DOI
Venue
2008
10.1016/j.patrec.2008.05.006
Pattern Recognition Letters
Keywords
Field
DocType
linear programming,different degree,distance measure,brain imaging,varying density,empirical evaluation,distance computation,distribution-based earth mover,activation pattern,content-based image retrieval,fmri image,fixed-radius distribution-based distance measure,content-based image retrieval application,fmri image matching,content-based fmri image retrieval,generalized family,image retrieval
Earth mover's distance,Image retrieval,Image processing,Robustness (computer science),Artificial intelligence,Time complexity,Computation,Computer vision,Pattern recognition,Algorithm,Mathematics,Content-based image retrieval,Distance measures
Journal
Volume
Issue
ISSN
29
12
Pattern Recognition Letters
Citations 
PageRank 
References 
0
0.34
5
Authors
7
Name
Order
Citations
PageRank
John Novatnack11135.90
Nicu D. Cornea242615.45
A. Shokoufandeh3135688.63
Deborah Silver456623.48
Sven J. Dickinson52836185.12
Paul Kantor6335.10
Bai, Bing7948.40