59 search results - page 8 / 12 » Trains of keypoints for 3D object recognition |
ECCV
2010
Springer
13 years 8 months ago
2010
Springer
In this paper we present a framework for semantic scene parsing and object recognition based on dense depth maps. Five viewindependent 3D features that vary with object class are e...
PAMI
2006
13 years 7 months ago
2006
In this paper, we propose two novel methods for face recognition under arbitrary unknown lighting by using spherical harmonics illumination representation, which require only one t...
ICPR
2008
IEEE
14 years 1 months ago
2008
IEEE
Boxes are the universal choice for packing, storage, and transportation. In this paper we propose a template-based algorithm for recognition of box-like objects, which is invarian...
ECCV
2004
Springer
14 years 26 days ago
2004
Springer
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
ECCV
2004
Springer
14 years 26 days ago
2004
Springer
This paper presents an analysis of the design of classifiers for use in a hierarchical object recognition approach. In this approach, a cascade of classifiers is arranged in a tr...