42 search results - page 1 / 9 » Incorporating Background Invariance into Feature-Based Objec... |
WACV
2005
IEEE
13 years 10 months ago
2005
IEEE
Current feature-based object recognition methods use information derived from local image patches. For robustness, features are engineered for invariance to various transformation...
SCIA
2007
Springer
13 years 10 months ago
2007
Springer
In this paper, we propose novel blur invariant features for the recognition of objects in images. The features are computed either using the phase-only spectrum or bispectrum of th...
ICPR
2008
IEEE
13 years 11 months ago
2008
IEEE
We present a novel method for incorporating prior knowledge about invariances in object recognition for discriminant analysis. In contrast to conventional isotropic regularization...
SSPR
1998
Springer
13 years 8 months ago
1998
Springer
Abstract. The increase in accessability to on-line visual data has promoted the interest in browsing and retrieval of images from Image Databases. Current approaches assume either ...
ICPR
2008
IEEE
13 years 11 months ago
2008
IEEE
Local invariant feature based methods have been proven to be effective in computer vision for object recognition and learning. But for an image, the number of points detected and ...