Sciweavers

Share
ICPR
2008
IEEE

CDIKP: A highly-compact local feature descriptor

10 years 3 months ago
CDIKP: A highly-compact local feature descriptor
A new feature descriptor is presented for object and scene recognition. The new approach, called CDIKP, uniquely combines the scale-invariant feature detection with a robust projection kernel technique to produce highly efficient feature representation. The produced feature descriptors are highly-compact in comparisons to the state-of-the-art, do not require any pre-training step, and show superior advantages in terms of distinctiveness, robustness to occlusions, invariance to scale, and tolerance of geometric distortions. We extensively evaluated the effectiveness of the new approach with various datasets acquired under varying circumstances.
Quan Wang, Suya You, Yun-Ta Tsai
Added 05 Nov 2009
Updated 06 Nov 2009
Type Conference
Year 2008
Where ICPR
Authors Quan Wang, Suya You, Yun-Ta Tsai
Comments (0)
books