Learning to detect natural image boundaries using local brightness, color, and texture cues
The goal of this work is to accurately detect and localize boundaries in
natural scenes using local image measurements. We formulate features that
respond to characteristic changes in brightness, color, and texture associated
with natural boundaries. In order to combine the information from these
features in an optimal way, we train a classifier using human labeled images as
ground truth. The output of this classifier provides the posterior probability
of a boundary at each image location and orientation. We present
precision-recall curves showing that the resulting detector significantly
outperforms existing approaches. Our two main results are 1) that cue
combination can be performed adequately with a simple linear model and 2) that
a proper, explicit treatment of texture is required to detect boundaries in
natural images.
Download: pdf
Text Reference
David R. Martin, Charless C. Fowlkes, and Jitendra Malik. Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE PAMI, 26(5):530–549, May 2004.BibTeX Reference
@article{MartinFM_PAMI_2003,AUTHOR = "Martin, David R. and Fowlkes, Charless C. and Malik, Jitendra",
TITLE = "Learning to detect natural image boundaries using local brightness, color, and texture cues",
JOURNAL = "IEEE PAMI",
VOLUME = "26",
YEAR = "2004",
NUMBER = "5",
MONTH = "May",
PAGES = "530-549",
TAG = "grouping",
BIBSOURCE = "http://www.visionbib.com/bibliography/segment351.html#TT24720"
}