Sciweavers

3641 search results - page 16 / 729
» On Computability of Pattern Recognition Problems
Sort
View
102
Voted
TASLP
2002
84views more  TASLP 2002»
15 years 2 months ago
Maximum likelihood multiple subspace projections for hidden Markov models
The first stage in many pattern recognition tasks is to generate a good set of features from the observed data. Usually, only a single feature space is used. However, in some compl...
Mark J. F. Gales
CVPR
2008
IEEE
16 years 4 months ago
A NURBS-based spectral reflectance descriptor with applications in computer vision and pattern recognition
In this paper, we present a surface reflectance descriptor based on the control points resulting from the interpolation of Non-Uniform Rational B-Spline (NURBS) curves to multispe...
Cong Phuoc Huynh, Antonio Robles-Kelly
145
Voted
ICPR
2004
IEEE
16 years 3 months ago
Using Multiple Graphics Cards as a General Purpose Parallel Computer : Applications to Computer Vision
Pattern recognition and computer vision tasks are computationally intensive, repetitive, and often exceed the capabilities of the CPU, leaving little time for higher level tasks. ...
James Fung, Steve Mann
ICIP
2009
IEEE
15 years 6 days ago
Learning weighted similarity measurements for unconstrained face recognition
Unconstrained face recognition is the problem of deciding if an image pair is showing the same individual or not, without having class specific training material or knowing anythi...
Andre Störmer, Gerhard Rigoll