Christopher M. Christoudias1,*, Bogdan Georgescu2 and Peter Meer1,2
1Department of Electrical and Computer Engineering,
Rutgers University, Piscataway New Jersey 08854
2Department of Computer Science,
Rutgers University, New brunswick New Jersey 08901
*Rutgers Undergraduate Research Fellow
Guiding image segmentation with edge information is an often employed strategy in low level computer vision. To improve the trade-off between the sensitivity of homogeneous region delineation and the oversegmentation of the image, we have incorporated a recently proposed edge magnitude/confidence map into a color image segmenter based on the mean shift procedure. The new method can recover regions with weak but sharp boundaries and thus can provide a more accurate input for high level interpretation modules. The Edge Detection and Image SegmentatiON (EDISON) system, available for download, implements the proposed technique and provides a complete toolbox for discontinuity preserving filtering, segmentation and edge detection.
The full text of this article was accepted for presentation at the 16th International Conference on Pattern Recognition. Track 1: Computer Vision and Robotics. Quebec City, Canada, August 2002. The text is presented here in pdf format. Interested readers will need Adobe Acrobat Reader to view the text.
|-- Go to the article (PDF version) --|
Copyright 2002 by Peter Meer
Current URL: http://rutgersscholar.rutgers.edu/volume04/chrimeer/chrimeer.htm