Systems Seminar
Mathematical and Perceptual Models for Image
Segmentation and Semantic Classification
Prof. Thrasos Pappas
EECS Department
Northwestern University
Abstract
We present a new approach for semantic image analysis that combines
knowledge of human perception with an understanding of signal
characteristics to segment natural scenes into perceptually uniform
regions, and then uses the region statistics to extract semantic
information that can be used for intelligent and efficient image
organization and retrieval. Our focus is on images of natural scenes.
One of the challenges of this problem is that the statistical
characteristics of perceptually uniform regions are spatially-varying
due to effects of lighting, perspective, scale changes, etc. We
present a new adaptive perceptual color-texture segmentation algorithm.
Key segmentation parameters are determined on the basis of subjective
tests. The color and texture features of the resulting regions are
used as medium level descriptors, based on which we extract semantic
labels. We also discuss the extension of these techniques to
video, and in particular, spatiotemporal segmentation and background
subtraction.
Bio
Thrasyvoulos (Thrasos) Pappas (http://www.eecs.northwestern.edu/~pappas)
received the S.B., S.M., and Ph.D. degrees in electrical engineering
and computer science from MIT in 1979, 1982, and 1987, respectively.
From 1987 until 1999, he was a Member of the Technical Staff at Bell
Laboratories, Murray Hill, NJ. In 1999, he joined the Department of
Electrical and Computer Engineering (now EECS) at Northwestern
University as an associate professor. His research interests are in
image and video quality and compression, perceptual models for image
processing, image and video analysis, model-based halftoning, and
multimedia signal processing.
Thrasos is a Fellow of the IEEE and SPIE. He is a member of the Board
of Governors of the Signal Processing Society of IEEE, and has served
as chair of the IEEE Image and Multidimensional Signal Processing
Technical Committee, associate editor of the IEEE Transactions on
Image Processing, and technical program co-chair of ICIP-01 and
IPSN-04 (Symposium on Information Processing in Sensor Networks).
Since 1997 he has been co-chair of the SPIE/IS&T Conference on Human
Vision and Electronic Imaging. He has also served as co-chair of the
2005 SPIE/IS&T Electronic Imaging Symposium.
Time and Place: Wed., Oct. 24, at 3:30 pm in 4610.
SYSTEMS SEMINAR WEB PAGE:
http://homepages.cae.wisc.edu/~gubner/seminar/schedule.html