Sciweavers

387 search results - page 68 / 78
» Generative versus Discriminative Methods for Object Recognit...
Sort
View
135
Voted
INFORMS
1998
100views more  INFORMS 1998»
15 years 3 months ago
Feature Selection via Mathematical Programming
The problem of discriminating between two nite point sets in n-dimensional feature space by a separating plane that utilizes as few of the features as possible, is formulated as a...
Paul S. Bradley, Olvi L. Mangasarian, W. Nick Stre...
ICPR
2006
IEEE
16 years 4 months ago
Supervised Image Classification by SOM Activity Map Comparison
This article presents a method aiming at quantifying the visual similarity between two images. This kind of problem is recurrent in many applications such as object recognition, i...
Grégoire Lefebvre, Christophe Laurent, Juli...
152
Voted
FGR
2008
IEEE
286views Biometrics» more  FGR 2008»
15 years 9 months ago
Complementary computing for visual tasks: Meshing computer vision with human visual processing
We explore the opportunity to harness electroencephalograph (EEG) signals generated during human visual processing to enhance computer vision systems. We review the challenging ta...
Ashish Kapoor, Desney S. Tan, Pradeep Shenoy, Eric...
ECCV
2004
Springer
15 years 8 months ago
Pose Invariant Face Recognition Under Arbitrary Unknown Lighting Using Spherical Harmonics
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...
Lei Zhang 0002, Dimitris Samaras
ICMCS
2005
IEEE
111views Multimedia» more  ICMCS 2005»
15 years 9 months ago
Enhancing curvature scale space features for robust shape classification
The curvature scale space (CSS) technique, which is also part of the MPEG-7 standard is a robust method to describe complex shapes.The central idea is to analyze the curvature of ...
Stephan Kopf, Thomas Haenselmann, Wolfgang Effelsb...