Continuous parametrization of normal distributions for improving the discrete statistical eigenspace approach for object recognition

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. This approach is used to improve the discrete statistical eigenspace approach for object recognition. The continuous parametrization of normal distributions allows an estimation of object poses where no training images were available. In an experiment with real objects we will show that our continuous approach leads to better localization and classification results than the discrete approach.