Sciweavers

1125 search results - page 21 / 225
» Object Recognition from Local Scale-Invariant Features
Sort
View
IJCNN
2008
IEEE
15 years 3 months ago
Feature selection based on kernel discriminant analysis for multi-class problems
— We propose a feature selection criterion based on kernel discriminant analysis (KDA) for an -class problem, which finds eigenvectors on which the projected class data are loca...
Tsuneyoshi Ishii, Shigeo Abe
AAAI
2004
14 years 11 months ago
Rapid Object Recognition from Discriminative Regions of Interest
Object recognition and detection represent a relevant component in cognitive computer vision systems, such as in robot vision, intelligent video surveillance systems, or multi-mod...
Gerald Fritz, Christin Seifert, Lucas Paletta, Hor...
SAC
2010
ACM
14 years 9 months ago
Visual processing-inspired fern-audio features for noise-robust speaker verification
In this paper, we consider the problem of speaker verification as a two-class object detection problem in computer vision, where the object instances are 1-D short-time spectral v...
Anindya Roy, Sébastien Marcel
WACV
2012
IEEE
13 years 5 months ago
CompactKdt: Compact signatures for accurate large scale object recognition
We present a novel algorithm, Compact Kd-Trees (CompactKdt), that achieves state-of-the-art performance in searching large scale object image collections. The algorithm uses an or...
Mohamed Aly, Mario E. Munich, Pietro Perona
BVAI
2005
Springer
15 years 3 months ago
Learning Location Invariance for Object Recognition and Localization
A visual system not only needs to recognize a stimulus, it also needs to find the location of the stimulus. In this paper, we present a neural network model that is able to genera...
Gwendid T. van der Voort van der Kleij, Frank van ...