Matching with shape contexts
Belongie, S.
Malik, J.
Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA;
This paper appears in: Content-based Access of Image and Video Libraries, 2000. Proceedings. IEEE Workshop on
Publication Date: 2000
On page(s): 20-26
Location: Hilton Head Island, SC, USA
ISBN: 0-7695-0695-X
References Cited: 32
INSPEC Accession Number: 6636456
Digital Object Identifier: 10.1109/IVL.2000.853834
Current Version Published: 2002-08-06
Abstract
We introduce a new shape descriptor, the shape context, for
measuring shape similarity and recovering point correspondences. The
shape context describes the coarse arrangement of the shape with respect
to a point inside or on the boundary of the shape. We use the shape
context as a vector-valued attribute in a bipartite graph matching
framework. Our proposed method makes use of a relatively small number of
sample points selected from the set of detected edges; no special
landmarks or keypoints are necessary. Tolerance and/or invariance to
common image transformations are available within our framework. Using
examples involving both silhouettes and edge images, we demonstrate how
the solution to the graph matching problem provides us with
correspondences and a dissimilarity score that can be used for object
recognition and similarity-based retrieval
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
