loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2005 IEEE International Conference on Multimedia and Expo
On the Earth Mover's Distance as a histogram similarity metric for image retrieval
Amsterdam, Netherlands
July 06-July 06
ISBN: 0-7803-9331-7
ASCII Text
x 
 
Z. Yu, G. Herman, "On the Earth Mover's Distance as a histogram similarity metric for image retrieval," Multimedia and Expo, IEEE International Conference on, pp. 4 pp., 2005 IEEE International Conference on Multimedia and Expo, 2005.
 
 
BibTex
x
 
@article{ 10.1109/ICME.2005.1521516,
author = {Z. Yu and G. Herman},
title = {On the Earth Mover's Distance as a histogram similarity metric for image retrieval},
journal ={Multimedia and Expo, IEEE International Conference on},
volume = {0},
year = {2005},
isbn = {0-7803-9331-7},
pages = {4 pp.},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICME.2005.1521516},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Multimedia and Expo, IEEE International Conference on
TI - On the Earth Mover's Distance as a histogram similarity metric for image retrieval
SN - 0-7803-9331-7
SP
EP
A1 - Z. Yu,
A1 - G. Herman,
PY - 2005
KW - adaptive binning histogram
KW - Earth movers distance
KW - EMD
KW - image retrieval
KW - frame extraction
KW - video shots
KW - random sampling
KW - quantitative evaluation
KW - clustering
VL - 0
JA - Multimedia and Expo, IEEE International Conference on
ER -
 
Z. Yu, Nat. ICT Australia, Sydney, NSW, Australia
G. Herman, Nat. ICT Australia, Sydney, NSW, Australia
In this paper, the performance of the Earth Mover's Distance (EMD) vs /spl chi//sup 2/ distance as histogram similarity metrics for image retrieval is evaluated experimentally. Ground truth is generated in two ways: through a novel approach of extracting frames from video shots and through random sampling. Quantitative evaluations of the retrieval performance with regular partitioning, clustered and adaptive binning histograms and with various number of bins are given. Meanwhile the influence of ground distance functions to the performance of the EMD is also studied. The findings of the paper may constitute guidelines in adopting the EMD.
Index Terms:
adaptive binning histogram, Earth movers distance, EMD, image retrieval, frame extraction, video shots, random sampling, quantitative evaluation, clustering
Citation:
Z. Yu, G. Herman, "On the Earth Mover's Distance as a histogram similarity metric for image retrieval," icme, pp.4 pp., 2005 IEEE International Conference on Multimedia and Expo, 2005
Usage of this product signifies your acceptance of the Terms of Use.