Object Recognition with 3D Models
Bernd Heisele, Gunhee Kim, Andrew J. Meyer · 2009
We propose techniques for designing and training of pose-invariant object recognition systems using realistic 3d computer graphics models. We look at the relation between the size of the training set and the classification accuracy for a basic recognition task and provide a method for estimating the degree of difficulty of detecting an object. We show how to sample, align, and cluster images of objects on the view sphere. We address the problem of training on large, highly redundant data and propose a novel active learning method which generates compact training sets and compact classifiers. © 2009. The copyright of this document resides with its authors.