DocumentCode
2488932
Title
Bregman sided and symmetrized centroids
Author
Nielsen, Frank ; Nock, Richard
Author_Institution
Sony Comput. Sci. Labs., Ecole Polytech., Palaiseau
fYear
2008
fDate
8-11 Dec. 2008
Firstpage
1
Lastpage
4
Abstract
We generalize the notions of centroids and barycenters to the broad class of information-theoretic distortion measures called Bregman divergences. Because Bregman divergences are typically asymmetric, we consider both the left-sided and right-sided centroids and the symmetrized centroids, and prove that all three are unique. We give closed-form solutions for the sided centroids that are generalized means, and design a provably fast and efficient approximation algorithm for the symmetrized centroid based on its exact geometric characterization that requires solely to walk on the geodesic linking the two sided centroids.
Keywords
approximation theory; computational geometry; content-based retrieval; feature extraction; image retrieval; Bregman divergence; approximation algorithm; barycenter centroid; closed-form solution; content-based multimedia retrieval application; feature extraction; geodesic linking; geometric characterization; image retrieval system; information-theoretic distortion measure; symmetrized centroid; Clustering algorithms; Content based retrieval; Distortion measurement; Euclidean distance; Feature extraction; Histograms; Image databases; Image retrieval; Multimedia databases; Multimedia systems;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 2008. ICPR 2008. 19th International Conference on
Conference_Location
Tampa, FL
ISSN
1051-4651
Print_ISBN
978-1-4244-2174-9
Electronic_ISBN
1051-4651
Type
conf
DOI
10.1109/ICPR.2008.4761794
Filename
4761794
Link To Document