Sciweavers

Share
CVPR
2000
IEEE

Towards Automatic Discovery of Object Categories

11 years 6 months ago
Towards Automatic Discovery of Object Categories
We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Our models represent objects as probabilistic constellations of rigid parts (features). The variability within a class is represented by a joint probability density function on the shape of the constellation and the appearance of the parts. Our method automatically identifies distinctive features in the training set. The set of model parameters is then learned using expectation maximization (see the companion paper [11] for details). When trained on different, unlabeled and unsegmented views of a class of objects, each component of the mixture model can adapt to represent a subset of the views. Similarly, different component models can also "specialize" on sub-classes of an object class. Experiments on images of human heads, leaves from different species of trees, and motor-cars demonstrate that the m...
Markus Weber, Max Welling, Pietro Perona
Added 12 Oct 2009
Updated 12 Oct 2009
Type Conference
Year 2000
Where CVPR
Authors Markus Weber, Max Welling, Pietro Perona
Comments (0)
books