How Much Does Globalization Help Segmentation?

by: Charless Fowlkes, Jitendra Malik

CSD-04-1340 (July 2004)

View FullText article

CiteSeer (at Penn State), CiteSeer (at MIT), CiteSeer (at Zurich), CiteSeer (at Singapore)

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

Vezhnick, zeppe, ooi

Find related articles with these CiteULike tags

ncuts, segmentation, spectral_segmentation, vision

Abstract

This paper quantifies the information gained in integrating local measurements using spectral graph partitioning. We employ a large dataset of manually segmented images in order to learn an optimal affinity function between nearby pairs of pixels. Region cues are computed as the similarity in brightness, color, and texture between image patches. Boundary cues are incorporated by looking for the presence of an "intervening contour", a large gradient along a straight line connecting two pixels....

@techreport{Fowlkes04NCuts, abstract = {This paper quantifies the information gained in integrating local measurements using spectral graph partitioning. We employ a large dataset of manually segmented images in order to learn an optimal affinity function between nearby pairs of pixels. Region cues are computed as the similarity in brightness, color, and texture between image patches. Boundary cues are incorporated by looking for the presence of an "intervening contour", a large gradient along a straight line connecting two pixels....}, author = {Fowlkes, Charless and Malik, Jitendra }, citeulike-article-id = {1369894}, institution = {Division of Computer Science, University of California, Berkeley}, journal = {CSD-04-1340}, keywords = {ncuts, segmentation, spectral\_segmentation}, month = {July}, posted-at = {2008-04-20 12:29:39}, priority = {4}, title = {How Much Does Globalization Help Segmentation?}, url = {http://citeseer.ist.psu.edu/fowlkes04how.html}, year = {2004} }

RIS record

TY - RPRT ID - Fowlkes04NCuts L3 - citeulike-article-id:1369894 TI - How Much Does Globalization Help Segmentation? JF - CSD-04-1340 N2 - This paper quantifies the information gained in integrating local measurements using spectral graph partitioning. We employ a large dataset of manually segmented images in order to learn an optimal affinity function between nearby pairs of pixels. Region cues are computed as the similarity in brightness, color, and texture between image patches. Boundary cues are incorporated by looking for the presence of an "intervening contour", a large gradient along a straight line connecting two pixels.... KW - ncuts KW - segmentation KW - spectral_segmentation AU - Fowlkes, Charless AU - Malik, Jitendra PY - 2004/07// UR - http://citeseer.ist.psu.edu/fowlkes04how.html ER -

RIS BibTeX