Shape matching and object recognition using shape contexts
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Shape matching and object recognition using shape contexts. / Belongie, Serge; Malik, Jitendra; Puzicha, Jan.
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 4, 04.2002, p. 509-522.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Shape matching and object recognition using shape contexts
AU - Belongie, Serge
AU - Malik, Jitendra
AU - Puzicha, Jan
N1 - Funding Information: This research is supported by the Army Research Office (ARO) DAAH04-96-1-0341, the Digital Library Grant IRI-9411334, a US National Science Foundation Graduate Fellowship for S. Belongie, and the Germ an Research Foundation by DFG grant PU-165/1. Parts of this work have appeared in [3], [2]. The authors wish to thank H. Chui and A. Rangarajan for providing the synthetic testing data used in Section 4.2. We would also like to thank them and various members of the Berkeley computer vision group, particularly A. Berg, A. Efros, D. Forsyth, T. Leung, J. Shi, and Y. Weiss, for useful discussions. This work was carried out while the authors were with the Departm ent of Electrical Engineering and Computer Science Division, University of California at Berkeley.
PY - 2002/4
Y1 - 2002/4
N2 - We present a novel approach to measuring similarity between shapes and exploit it for object recognition. In our framework, the measurement of similarity is preceded by 1) solving for correspondences between points on the two shapes, 2) using the correspondences to estimate an aligning transform. In order to solve the correspondence problem, we attach a descriptor, the shape context, to each point. The shape context at a reference point captures the distribution of the remaining points relative to it, thus offering a globally discriminative characterization. Corresponding points on two similar shapes will have similar shape contexts, enabling us to solve for correspondences as an optimal assignment problem. Given the point correspondences, we estimate the transformation that best aligns the two shapes; regularized thin-plate splines provide a flexible class of transformation maps for this purpose. The dissimilarity between the two shapes is computed as a sum of matching errors between corresponding points, together with a term measuring the magnitude of the aligning transform. We treat recognition in a nearest-neighbor classification framework as the problem of finding the stored prototype shape that is maximally similar to that in the image. Results are presented for silhouettes, trademarks, handwritten digits, and the COIL data set.
AB - We present a novel approach to measuring similarity between shapes and exploit it for object recognition. In our framework, the measurement of similarity is preceded by 1) solving for correspondences between points on the two shapes, 2) using the correspondences to estimate an aligning transform. In order to solve the correspondence problem, we attach a descriptor, the shape context, to each point. The shape context at a reference point captures the distribution of the remaining points relative to it, thus offering a globally discriminative characterization. Corresponding points on two similar shapes will have similar shape contexts, enabling us to solve for correspondences as an optimal assignment problem. Given the point correspondences, we estimate the transformation that best aligns the two shapes; regularized thin-plate splines provide a flexible class of transformation maps for this purpose. The dissimilarity between the two shapes is computed as a sum of matching errors between corresponding points, together with a term measuring the magnitude of the aligning transform. We treat recognition in a nearest-neighbor classification framework as the problem of finding the stored prototype shape that is maximally similar to that in the image. Results are presented for silhouettes, trademarks, handwritten digits, and the COIL data set.
KW - Correspondence problem
KW - Deformable templates
KW - Digit recognition
KW - Image registration
KW - MPEG7
KW - Object recognition
KW - Shape
UR - http://www.scopus.com/inward/record.url?scp=0036538619&partnerID=8YFLogxK
U2 - 10.1109/34.993558
DO - 10.1109/34.993558
M3 - Journal article
AN - SCOPUS:0036538619
VL - 24
SP - 509
EP - 522
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
SN - 0162-8828
IS - 4
ER -
ID: 302058015