THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
Matt Boutell (Graduate Student )
UR > CS > Research > Vision > People > Matt Boutell
 in action

Contact:

Matt Boutell
CSB 620
Department of Computer Science
University of Rochester
Rochester, NY 14627

vox: (716) 275-5492
email: boutell@cs.rochester.edu
home: http://www.cs.rochester.edu/~boutell
vision: http://www.rochester.edu/research/vision/people/Matthew_R_Boutell

About:

Matt is in the third year of the Ph.D. program in Computer Science at the Univesity of Rochester. He is proposing a thesis on Semantic Scene Classification with Chris Brown. He spends most every other waking moment with his wife and three beautiful children. When presented with a rare free moment, he enjoys Bible study, reading, shovelling snow (hence Rochester!), singing bass, and playing tuba.

Research Interests:

My research interests include machine intelligence, probabilistic inference, and pattern recognition. Semantic scene classification is part of a larger effort to understand the content of real images, and lies at the intersection of my broader interests. In my thesis, I am seeking to bridge the gap between the low-level pixel representation of an image and the high level understanding of it. Our framework relies on semantic material detection as a middle ground and adds to it spatial scene models which may be used to infer the category of the scene.

Projects:

Semantic Scene Classification: We improve semantic scene classification by using semantic object/ material detectors and spatial models within a probabilistic framework to infer the scene type.


Publications:

Review of the State of the Are in Semantic Scene Classification (Matthew R. Boutell)
Sunset Scene Classification Using Simulated Image Recomposition (Matthew Boutell and Jiebo Luo and Robert T. Gray)