Universität Bielefeld - Sonderforschungsbereich 360

Towards a theory of recognition of visual classes

Pietro Perona, California Institute of Technology

We may classify an object as a car without knowing its make and model, as a face without recognizing its owner. Objects belonging to the same class may look quite different in detail; however, they often share some visual properties that allow us to classify them based on their appearance.

I will present an approach to recognizing such visual classes. It is based on combining in a probabilitstic framework visual information about the appearance of local features of an object with metric information about their spatial relationship.

Experimental resultes on an application of our ideas to detecting human faces in cluttered scenes will be presented. Our algorithm is shown to have approximately 95% correct localization rate on a large challenging database containing faces in complicated and varied backgrounds.

In collaboration with M. Burl and T. Leung and M. Weber.

Anke Weinberger, 1997-06-06