We propose the use of latent space models applied to local invariant features for object classification. We investigate whether using latent space models enables to learn patterns...
Florent Monay, Pedro Quelhas, Daniel Gatica-Perez,...
We develop a novel method for class-based feature matching across large changes in viewing conditions. The method (called MBE) is based on the property that when objects share a si...
Abstract. For real time object recognition and tracking often color-based methods are used. While these methods are very efficient, they usually dependent heavily on lighting cond...
Thilo Weigel, Dapeng Zhang 0002, Klaus Rechert, Be...
Ageometric framework for the recognition of three-dimensional objects represented by point
clouds is introducedin this paper. The proposed approach is based on comparing distribut...
Noisy or distorted video/audio training sets represent constant challenges in automated identification and verification tasks. We propose the method of Mutual Interdependence An...