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...
In this paper, we propose a method of estimating camera parameters for annotating 3D virtual objects with a wearable vision system. The proposed method tracks natural feature poin...
In this paper we study interest point descriptors for image matching and 3D reconstruction. We examine the building blocks of descriptor algorithms and evaluate numerous combinati...
A homogeneous paradigm for evidence integration is presented, and a vision system to recognize 3D objects is demonstrated using this paradigm. A new concept called generalizedfeat...
Rick Kjeldsen, Ruud M. Bolle, Andrea Califano, Rus...
We present a method for the recovery of partially occluded 3D geometric primitives from range images which might also include non-primitive objects. The method uses a technique for...