J. Shi, and J. Malik. IEEE Trans. on Pattern Analysis and Machine Intelligence, 22 (8):
888-905(2000)
DOI: 10.1109/34.868688
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
Description
Welcome to IEEE Xplore 2.0: Normalized cuts and image segmentation
%0 Journal Article
%1 Shi00normalizedCuts
%A Shi, Jianbo
%A Malik, J.
%D 2000
%J IEEE Trans. on Pattern Analysis and Machine Intelligence
%K 00 Shi clustering cuts graph min-cut normalized
%N 8
%P 888-905
%R 10.1109/34.868688
%T Normalized cuts and image segmentation
%V 22
%X 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
@article{Shi00normalizedCuts,
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},
added-at = {2009-01-11T23:05:22.000+0100},
author = {Shi, Jianbo and Malik, J.},
biburl = {https://www.bibsonomy.org/bibtex/2ced43e4f3bc696c3bd58671087da1c5d/lee_peck},
description = {Welcome to IEEE Xplore 2.0: Normalized cuts and image segmentation},
doi = {10.1109/34.868688},
interhash = {b9dfec1e25c24c6e4c62990ca15d00ab},
intrahash = {ced43e4f3bc696c3bd58671087da1c5d},
issn = {0162-8828},
journal = {IEEE Trans. on Pattern Analysis and Machine Intelligence},
keywords = {00 Shi clustering cuts graph min-cut normalized},
number = 8,
pages = {888-905},
timestamp = {2009-01-11T23:05:23.000+0100},
title = {Normalized cuts and image segmentation},
volume = 22,
year = 2000
}