Locally uniform comparison image descriptor
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Locally uniform comparison image descriptor. / Ziegler, Andrew; Christiansen, Eric; Kriegman, David; Belongie, Serge.
In: Advances in Neural Information Processing Systems, 2012, p. 1-9.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Locally uniform comparison image descriptor
AU - Ziegler, Andrew
AU - Christiansen, Eric
AU - Kriegman, David
AU - Belongie, Serge
PY - 2012
Y1 - 2012
N2 - Keypoint matching between pairs of images using popular descriptors like SIFT or a faster variant called SURF is at the heart of many computer vision algorithms including recognition, mosaicing, and structure from motion. However, SIFT and SURF do not perform well for real-time or mobile applications. As an alternative very fast binary descriptors like BRIEF and related methods use pairwise comparisons of pixel intensities in an image patch. We present an analysis of BRIEF and related approaches revealing that they are hashing schemes on the ordinal correlation metric Kendall's tau. Here, we introduce Locally Uniform Comparison Image Descriptor (LUCID), a simple description method based on linear time permutation distances between the ordering of RGB values of two image patches. LUCID is computable in linear time with respect to the number of pixels and does not require floating point computation.
AB - Keypoint matching between pairs of images using popular descriptors like SIFT or a faster variant called SURF is at the heart of many computer vision algorithms including recognition, mosaicing, and structure from motion. However, SIFT and SURF do not perform well for real-time or mobile applications. As an alternative very fast binary descriptors like BRIEF and related methods use pairwise comparisons of pixel intensities in an image patch. We present an analysis of BRIEF and related approaches revealing that they are hashing schemes on the ordinal correlation metric Kendall's tau. Here, we introduce Locally Uniform Comparison Image Descriptor (LUCID), a simple description method based on linear time permutation distances between the ordering of RGB values of two image patches. LUCID is computable in linear time with respect to the number of pixels and does not require floating point computation.
UR - http://www.scopus.com/inward/record.url?scp=84877775561&partnerID=8YFLogxK
UR - https://papers.nips.cc/paper/2012/hash/c20ad4d76fe97759aa27a0c99bff6710-Abstract.html
M3 - Conference article
AN - SCOPUS:84877775561
SP - 1
EP - 9
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
SN - 1049-5258
T2 - 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012
Y2 - 3 December 2012 through 6 December 2012
ER -
ID: 301829993