Normalized cuts and image segmentation

Normalized cuts and image segmentation (2000)

by Jianbo Shi , Jitendra Malik

Citations:

User correction supplied by mph

Datum	Value	Source
TITLE	Normalized cuts and image segmentation	INFERENCE
AUTHOR NAME	Jianbo Shi	user correction
AUTHOR NAME	Jitendra Malik	user correction
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 have applied this approach to segmenting static images, as well as motion sequences, and found the results to be very encouraging.	user correction
YEAR	2000	INFERENCE
VENUE TYPE	TECHREPORT	INFERENCE
TECH	PAMI	INFERENCE
CITATIONS	25 found	ParsCit 1.0