TY - GEN
T1 - Combining color and geometry for local image matching
AU - Mazin, Baptiste
AU - Delon, Julie
AU - Gousseau, Yann
PY - 2012/12/1
Y1 - 2012/12/1
N2 - This paper introduces a generic way to incorporate color information into local, SIFT-like descriptors, in view of image matching. First, a new color descriptor, relying on local hue histograms, is introduced. Second, we describe a procedure permitting the automatic setting of matching parameters when matching images using both geometric and color information. Experiments on a color image database show that our SIFT+Hue combination performs significantly better than classical color descriptors.
AB - This paper introduces a generic way to incorporate color information into local, SIFT-like descriptors, in view of image matching. First, a new color descriptor, relying on local hue histograms, is introduced. Second, we describe a procedure permitting the automatic setting of matching parameters when matching images using both geometric and color information. Experiments on a color image database show that our SIFT+Hue combination performs significantly better than classical color descriptors.
M3 - Conference contribution
AN - SCOPUS:84874564000
SN - 9784990644109
T3 - Proceedings - International Conference on Pattern Recognition
SP - 2677
EP - 2680
BT - ICPR 2012 - 21st International Conference on Pattern Recognition
T2 - 21st International Conference on Pattern Recognition, ICPR 2012
Y2 - 11 November 2012 through 15 November 2012
ER -