Task specific local region matching
Research output: Contribution to conference › Paper › Research › peer-review
Standard
Task specific local region matching. / Babenko, Boris; Dollár, Piotr; Belongie, Serge.
2007. Paper presented at 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brazil.Research output: Contribution to conference › Paper › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - CONF
T1 - Task specific local region matching
AU - Babenko, Boris
AU - Dollár, Piotr
AU - Belongie, Serge
PY - 2007
Y1 - 2007
N2 - Many problems in computer vision require the knowledge of potential point correspondences between two images. The usual approach for automatically determining correspondences begins by comparing small neighborhoods of high saliency in both images. Since speed is of the essence, most current approaches for local region matching involve the computation of a feature vector that is invariant to various geometric and photometric transformations, followed by fast distance computations using standard vector norms. These algorithms include many parameters, and choosing an algorithm and setting its parameters for a given problem is more an art than a science. Furthermore, although invariance of the resulting feature space is in general desirable, there is necessarily a tradeoff between invariance and descriptiveness for any given task. In this paper we pose local region matching as a classification problem, and use powerful machine learning techniques to train a classifier that selects features from a much larger pool. Our algorithm can be trained on specific domains or tasks, and performs better than the state of the art in such cases. Since our method is an application of boosting, we refer to it as Boosted Region Matching (BOOM).
AB - Many problems in computer vision require the knowledge of potential point correspondences between two images. The usual approach for automatically determining correspondences begins by comparing small neighborhoods of high saliency in both images. Since speed is of the essence, most current approaches for local region matching involve the computation of a feature vector that is invariant to various geometric and photometric transformations, followed by fast distance computations using standard vector norms. These algorithms include many parameters, and choosing an algorithm and setting its parameters for a given problem is more an art than a science. Furthermore, although invariance of the resulting feature space is in general desirable, there is necessarily a tradeoff between invariance and descriptiveness for any given task. In this paper we pose local region matching as a classification problem, and use powerful machine learning techniques to train a classifier that selects features from a much larger pool. Our algorithm can be trained on specific domains or tasks, and performs better than the state of the art in such cases. Since our method is an application of boosting, we refer to it as Boosted Region Matching (BOOM).
UR - http://www.scopus.com/inward/record.url?scp=50649114604&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2007.4408848
DO - 10.1109/ICCV.2007.4408848
M3 - Paper
AN - SCOPUS:50649114604
T2 - 2007 IEEE 11th International Conference on Computer Vision, ICCV
Y2 - 14 October 2007 through 21 October 2007
ER -
ID: 302051923