Matt Boutell's Research and Selected Publications
Summary: My primary interest is in understanding of
digital home photographs, especially semantic scene
classification. Most of my research involves using various types
of context. I have also
worked on determining image orientation, and on
general issues involved in learning by example.
More broadly, I am interested in image understanding, computer vision
and computer graphics. Over the past few years, my primary collaborators
have been my co-advisors,
Chris Brown of the University of Rochester and Jiebo
Luo of Eastman Kodak Company.
While unconstrained object recognition is an open problem, how can we
extract enough information about a scene to classify it robustly as a
beach scene, a sunset, or a party scene? For my master's thesis, I
surveyed the state of the art (in 2002). Portions appear in
the following URCS Technical Report. We also wrote a paper comparing semantic features
(such as the output from sky, grass, and other detectors) to low-level features.
- Matthew Boutell, Christopher Brown, and Jiebo Luo. Survey on the
state of the art in semantic scene classification. Technical Report
799, University of Rochester, Rochester, NY, December 2002. pdf
- Matthew Boutell, Anustup Choudhury, Jiebo Luo, and Christopher Brown.
Using semantic features for scene classification: How good do they need to be?
IEEE International Conference on Multimedia and Expo, Toronto, July 2006.
[pdf]
My primary contribution to semantic scene classification is
demonstrating the utility of context for classifying
scenes. Each of these papers investigates using some type of context,
whether temporal (from image collections), spatial (relationships
between regions in the same scene), or camera (metadata tags about
scene capture properties, such as exposure time and subject distance).
- Matthew Boutell and Jiebo Luo. Beyond pixels: Exploiting camera
metadata for photo classification. Pattern Recognition, Special
Issue on Image Understanding for Digital Photos, to appear. draft pdf
- Matthew Boutell, Jiebo Luo, and Christopher Brown. Factor-graphs for
region-based whole-scene classification. International Workshop on
Semantic Learning Applications in Multimedia (in conjunction with CVPR2006),
New York, NY, June 2006. [pdf]
- Matthew Boutell, Jiebo Luo, and Christopher Brown. Learning
spatial configuration models using modified Dirichlet priors.
2004 Workshop on Statistical Relational Learning (in conjunction
with ICML2004), Banff, Alberta, July 2004. [pdf]
- Matthew Boutell and Jiebo Luo. Bayesian fusion of camera metadata
cues in semantic scene classification. 2004 IEEE Conference on
Computer Vision and Pattern Recognition, Washington, DC. [pdf]
- Matthew Boutell and Jiebo Luo. Incorporating temporal context
with content for classifying image collections. 2004
International Conference on Pattern Recognition, Cambridge, UK.
[pdf]
In these papers, we extend learning by example in two areas: handling
multilabel scenes in training and testing, and using image transforms
to recompose images, both for training and testing.
- Matthew Boutell, Xipeng Shen, Jiebo Luo, and Christopher Brown.
Learning multi-label semantic scene classification. Pattern
Recognition, 37(9), pp. 1757-1771, September 2004. pdf
- Matthew Boutell, Jiebo Luo, and Robert T. Gray. Sunset scene
classification using simulated image recomposition.
International Conference on Multimedia and Expo, June 2003.
[pdf]
Automatically determining the orientation of home photos is a
difficult problem. The first paper documents a study of the accuracy
of human observers on the problem and the cues they use. The second
describes a vision system that integrates both low-level and semantic
cues to solve the problem.
- Jiebo Luo, David Crandall, Amit Singhal, Matthew Boutell, and
Robert T. Gray. Psychophysical study of image orientation
perception. Spatial Vision, 16(5), pp. 429-457, December
2003. [pdf]
- Jiebo Luo and Matthew Boutell. A probabilistic approach to image
orientation detection via confidence-based integration of low-level
and semantic cues. 4th International Workshop on Multimedia Data
and Document Engineering (in conjunction with CVPR 2004),
Washington, DC, 2004. An expanded version of this work will
appear in the Transactions on Pattern Analysis and Machine
Intelligence. [pdf]
Copyright notice
This material is presented to ensure timely
dissemination of scholarly and technical work. Copyright and all
rights therein are retained by authors or by other copyright
holders. All persons copying this information are expected to adhere
to the terms and constraints invoked by each author's copyright. These
works may not be reposted without the explicit permission of the
copyright holder.
Return to main page