Unsupervised estimation of segmentation quality using nonnegative factorization

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Roman Sandler Articles by Michael Lindenbaum

2008 IEEE Conference on Computer Vision and Pattern Recognition

Anchorage, AK, USA

June 23-June 28

ISBN: 978-1-4244-2242-5

	ASCII Text	x
	Roman Sandler, Michael Lindenbaum, "Unsupervised estimation of segmentation quality using nonnegative factorization," Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, pp. 1-8, 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008.

	BibTex	x
	@article{ 10.1109/CVPR.2008.4587439, author = {Roman Sandler and Michael Lindenbaum}, title = {Unsupervised estimation of segmentation quality using nonnegative factorization}, journal ={Computer Vision and Pattern Recognition, IEEE Computer Society Conference on}, volume = {0}, year = {2008}, isbn = {978-1-4244-2242-5}, pages = {1-8}, doi = {http://doi.ieeecomputersociety.org/10.1109/CVPR.2008.4587439}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Computer Vision and Pattern Recognition, IEEE Computer Society Conference on TI - Unsupervised estimation of segmentation quality using nonnegative factorization SN - 978-1-4244-2242-5 SP1 EP8 A1 - Roman Sandler, A1 - Michael Lindenbaum, PY - 2008 VL - 0 JA - Computer Vision and Pattern Recognition, IEEE Computer Society Conference on ER -

Roman Sandler, Computer Science dept. Technion, Haifa 32000, Israel

Michael Lindenbaum, Computer Science dept. Technion, Haifa 32000, Israel

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CVPR.2008.4587439

We propose an unsupervised method for evaluating image segmentation. Common methods are typically based on evaluating smoothness within segments and contrast between them, and the measure they provide is not explicitly related to segmentation errors. The proposed approach differs from these methods on several important points and has several advantages over them.

Citation:

Roman Sandler, Michael Lindenbaum, "Unsupervised estimation of segmentation quality using nonnegative factorization," cvpr, pp.1-8, 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.