Normalized cuts and image segmentation
Jianbo Shi
Malik, J.
Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Aug 2000
Volume: 22,
Issue: 8
On page(s): 888-905
ISSN: 0162-8828
References Cited: 25
CODEN: ITPIDJ
INSPEC Accession Number: 6744979
Digital Object Identifier: 10.1109/34.868688
Current Version Published: 2002-08-06
Abstract
We propose a novel approach for solving the perceptual grouping
problem in vision. Rather than focusing on local features and their
consistencies in the image data, our approach aims at extracting the
global impression of an image. We treat image segmentation as a graph
partitioning problem and propose a novel global criterion, the
normalized cut, for segmenting the graph. The normalized cut criterion
measures both the total dissimilarity between the different groups as
well as the total similarity within the groups. We show that an
efficient computational technique based on a generalized eigenvalue
problem can be used to optimize this criterion. We applied this approach
to segmenting static images, as well as motion sequences, and found the
results to be very encouraging
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
