A Bayesian approach to visual size classification of everyday objects

Publication Type:

Conference Paper


T. McDaniel, K. Kahol, S. Panchanathan


IEEE International Conference on Pattern Recognition (ICPR), Volume 2, Hong Kong, p.255-259 (2006)




Humans are adept at size classification from visual images of objects. A challenging computer vision problem is that of automatic visual size classification. Current size classification systems assume controlled environments and use features geared towards a particular object category and pose. However, certain applications may require algorithms that can adapt to a variety of object categories and handle complex environments. In this paper, we propose a Bayesian approach to automatic visual size classification, inspired by human visual perception, for a more generalized and robust size classifier. Initial results show that the proposed approach can handle multiple object categories and is invariant to scale changes.


Dr. Troy L. McDaniel

Dr. Troy L. McDaniel

Assistant Professor, The Polytechnic School; Director, HAPT-X Laboratory; Co-Director, Center for Cognitive Ubiquitous Computing (CUbiC); Co-PI, NSF-NRT grant program, Citizen-Centered Smart Cities and Smart Living

Dr. Sethuraman "Panch" Panchanathan

Dr. Sethuraman "Panch" Panchanathan

Director, National Science Foundation