The Robotics Institute

My primary interest is in the intelligence of perception. Specifically, I study computer vision, pattern recognition and machine learning, with an emphasis on statistical methods and their practical applications.

My Ph.D. thesis work involves matching articulated object models to still images. The human body is a typical example of a nonrigid, articulated object. Body localization has a 20-year history in computer vision, yet remains one of the fundamental unsolved problems. Currently I am studying this problem in a generic setting: single image, arbitrary pose, and arbitrary viewpoint.

Some other problems I have worked on include: OCR and handwriting recognition, cervical cancer diagnosis, and feature extraction/selection.