How Much Does Globalization Help Segmentation?
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. We then use spectral clustering to find an
approximate minimizer of the normalized cut, partitioning the image into
coherent segments.
We evaluate the power of local measurements and global segmentations in
predicting the location of image boundaries by computing the precision and
recall with respect to the human groundtruth data. The results show that
spectral clustering is successful in suppressing noise and boosting weak
signals over a wide variety of natural images.
Download: pdf
Text Reference
Charless C. Fowlkes and Jitendra Malik. How much does globalization help segmentation? Technical Report UCB//CSD-04-1340, UC Berkeley, 2004.BibTeX Reference
@TechReport{FowlkesM_TR_2004,author = "Fowlkes, Charless C. and Malik, Jitendra",
title = "How Much Does Globalization Help Segmentation?",
institution = "UC Berkeley",
number = "UCB//CSD-04-1340",
year = "2004",
tag = "grouping"
}