My research has spanned a range of topics in vision.  My primary focus has been on the problem of recognizing objects in images.  My recent work has mainly focused on understanding how to recognize objects under varying lighting conditions, varying poses, and how to model the non-rigid deformation of objects and use these models to match images.  I have also been interested in a variety of other problems in vision, including image clustering and structure-from-motion, and in the intersection between vision and user interfaces and vision and graphics.  Our group is applying some of this work to building electronic field guides.  Our iphone app, Leafsnap has been downloaded by more than 1,500,000 users.  We have also developed Birdsnap and Dogsnap.