Continuous Parametrization of Normal Distributions for Improving the Discrete Statistical Eigenspace Approach for Object Recognition
by
Ch. Gräßl
,
F. Deinzer
,
H. Niemann
| Citations: | 2 - 0 self |
BibTeX
@MISC{Gräßl_continuousparametrization,
author = {Ch. Gräßl and F. Deinzer and H. Niemann},
title = {Continuous Parametrization of Normal Distributions for Improving the Discrete Statistical Eigenspace Approach for Object Recognition},
year = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Statistical approaches play an important role in computer vision, normal distributions especially are widely used. In this paper we present a new approach for a continuous parametrization of normal distributions. Our method is based on arbitrary interpolation techniques.
Citations
| 846 | Visual learning and recognition of 3-d objects from appearance - Murase, Nayar - 1995 |
| 236 | Probability Theory - Loéve - 1955 |
| 168 | Global optimization - Törn, Zilinskas - 1989 |
| 36 | A class of local interpolating splines. Computer Aided Geometric Design - CATMULL, ROM - 1974 |
| 19 | A.: Active object recognition by view integration and reinforcement learning. Robotics and Autonomous Systems 31 - Paletta, Pinz - 2000 |
| 17 | Statistical learning, localization and identification of objects - Hornegger - 1995 |
| 10 | Discriminative Training of Gaussian Mixtures for Image Object Recognition - Dahmen, Schlüter, et al. - 1999 |
| 5 | Active appearance-based object recognition using viewpoint selection - Reinhold, Deinzer, et al. - 2000 |
| 4 | On Fusion of Multiple Views for Active Object Recognition - Deinzer, Denzler, et al. - 2001 |
| 3 | Image Database for 3-D Object Recognition - Drexler, Niemann - 2001 |
