This paper presents a novel method for quickly filtering range data points to make object recognition in large 3D data sets feasible. The general approach, called "3D cueing,...
We propose a multiple classifier system approach to object recognition in computer vision. The aim of the approach is to use multiple experts successively to prune the list of cand...
Recognition of specular objects is particularly difficult because their appearance is much more sensitive to lighting changes than that of Lambertian objects. We consider an appr...
We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an ob...
Software available at http://disi.unitn.it/~uijlings or http://koen.me/research/
For object recognition, the current state-of-the-art is based on exhaustive search. However, to ...