How Much Does Globalization Help Segmentation?
Charless Fowlkes, Jitendra Malik
icon 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"
}