TY - GEN
T1 - SIFT-rank
T2 - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
AU - Toews, Matthew
AU - William, Wells
PY - 2009
Y1 - 2009
N2 - This paper investigates ordinal image description for invariant feature correspondence. Ordinal description is a meta-technique which considers image measurements in terms of their ranks in a sorted array, instead of the measurement values themselves. Rank-ordering normalizes descriptors in a manner invariant under monotonic deformations of the underlying image measurements, and therefore serves as a simple, non-parametric substitute for ad hoc scaling and thresholding techniques currently used. Ordinal description is particularly well-suited for invariant features, as the high dimensionality of state-of-the-art descriptors permits a large number of unique rank-orderings, and the computationally complex step of sorting is only required once after geometrical normalization. Correspondence trials based on a benchmark data set show that in general, rank-ordered SIFT (SIFT-Rank) descriptors outperform other state-of-the-art descriptors in terms of precisionrecall, including standard SIFT and GLOH.
AB - This paper investigates ordinal image description for invariant feature correspondence. Ordinal description is a meta-technique which considers image measurements in terms of their ranks in a sorted array, instead of the measurement values themselves. Rank-ordering normalizes descriptors in a manner invariant under monotonic deformations of the underlying image measurements, and therefore serves as a simple, non-parametric substitute for ad hoc scaling and thresholding techniques currently used. Ordinal description is particularly well-suited for invariant features, as the high dimensionality of state-of-the-art descriptors permits a large number of unique rank-orderings, and the computationally complex step of sorting is only required once after geometrical normalization. Correspondence trials based on a benchmark data set show that in general, rank-ordered SIFT (SIFT-Rank) descriptors outperform other state-of-the-art descriptors in terms of precisionrecall, including standard SIFT and GLOH.
UR - https://www.scopus.com/pages/publications/70450192064
U2 - 10.1109/CVPRW.2009.5206849
DO - 10.1109/CVPRW.2009.5206849
M3 - Contribution to conference proceedings
AN - SCOPUS:70450192064
SN - 9781424439935
T3 - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
SP - 172
EP - 177
BT - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
PB - IEEE Computer Society
Y2 - 20 June 2009 through 25 June 2009
ER -