DMCA
Efficient Image Segmentation Using Pairwise Pixel Similarities
| Citations: | 2 - 1 self |
BibTeX
@MISC{Rohkohl_efficientimage,
author = {Christopher Rohkohl and Karin Engel},
title = {Efficient Image Segmentation Using Pairwise Pixel Similarities},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. Image segmentation based on pairwise pixel similarities has been a very active field of research in recent years. The drawbacks common to these segmentation methods are the enormous space and processor requirements. The contribution of this paper is a general purpose two-stage preprocessing method that substantially reduces the involved costs. Initially, an oversegmentation into small coherent image patches-or superpixels- is obtained through an iterative process guided by pixel similarities. A suitable pairwise superpixel similarity measure is then defined which may be plugged into an arbitrary segmentation method based on pairwise pixel similarities. To illustrate our ideas we integrated the algorithm into a spectral graph-partitioning method using the Normalized Cut criterion. Our experiments show that the time and memory requirements are reduced drastically (> 99%), while segmentations of adequate quality are obtained. 1
Keyphrases
pairwise pixel similarity general purpose two-stage active field spectral graph-partitioning method image segmentation normalized cut criterion iterative process recent year enormous space processor requirement arbitrary segmentation method involved cost adequate quality memory requirement small coherent image patches-or superpixels segmentation method suitable pairwise superpixel similarity measure pixel similarity
