Matching with shape contexts
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Matching with shape contexts. / Belongie, S.; Malik, J.
In: Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2000, 2000, p. 20-26.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Matching with shape contexts
AU - Belongie, S.
AU - Malik, J.
N1 - Publisher Copyright: © 2000 IEEE.
PY - 2000
Y1 - 2000
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84959859697&partnerID=8YFLogxK
U2 - 10.1109/IVL.2000.853834
DO - 10.1109/IVL.2000.853834
M3 - Conference article
AN - SCOPUS:84959859697
SP - 20
EP - 26
JO - Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2000
JF - Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2000
T2 - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2000
Y2 - 12 June 2000
ER -
ID: 302169527