Abstract
We propose a novel Riemannian framework for comparing signals and images in a manner that is invariant to their levels of blur. This framework uses a log-Fourier representation of signals/images in which the set of all possible Gaussian blurs of a signal, i.e. its orbits under semigroup action of Gaussian blur functions, is a straight line. Using a set of Riemannian metrics under which the group actions are by isometries, the orbits are compared via distances between orbits. We demonstrate this framework using a number of experimental results involving 1D signals and 2D images.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings of the IEEE International Conference on Computer Vision |
| Pages | 1770-1775 |
| Number of pages | 6 |
| DOIs | |
| State | Published - 2011 |
| Externally published | Yes |
| Event | 2011 IEEE International Conference on Computer Vision, ICCV 2011 - Barcelona, Spain Duration: Nov 6 2011 → Nov 13 2011 |
Other
| Other | 2011 IEEE International Conference on Computer Vision, ICCV 2011 |
|---|---|
| Country | Spain |
| City | Barcelona |
| Period | 11/6/11 → 11/13/11 |
Fingerprint
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
Cite this
Blurring-invariant Riemannian metrics for comparing signals and images. / Zhang, Zhengwu; Klassen, Eric; Srivastava, Anuj; Turaga, Pavan; Chellappa, Rama.
Proceedings of the IEEE International Conference on Computer Vision. 2011. p. 1770-1775 6126442.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Blurring-invariant Riemannian metrics for comparing signals and images
AU - Zhang, Zhengwu
AU - Klassen, Eric
AU - Srivastava, Anuj
AU - Turaga, Pavan
AU - Chellappa, Rama
PY - 2011
Y1 - 2011
N2 - We propose a novel Riemannian framework for comparing signals and images in a manner that is invariant to their levels of blur. This framework uses a log-Fourier representation of signals/images in which the set of all possible Gaussian blurs of a signal, i.e. its orbits under semigroup action of Gaussian blur functions, is a straight line. Using a set of Riemannian metrics under which the group actions are by isometries, the orbits are compared via distances between orbits. We demonstrate this framework using a number of experimental results involving 1D signals and 2D images.
AB - We propose a novel Riemannian framework for comparing signals and images in a manner that is invariant to their levels of blur. This framework uses a log-Fourier representation of signals/images in which the set of all possible Gaussian blurs of a signal, i.e. its orbits under semigroup action of Gaussian blur functions, is a straight line. Using a set of Riemannian metrics under which the group actions are by isometries, the orbits are compared via distances between orbits. We demonstrate this framework using a number of experimental results involving 1D signals and 2D images.
UR - http://www.scopus.com/inward/record.url?scp=84863042732&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84863042732&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2011.6126442
DO - 10.1109/ICCV.2011.6126442
M3 - Conference contribution
SN - 9781457711015
SP - 1770
EP - 1775
BT - Proceedings of the IEEE International Conference on Computer Vision
ER -