Share Email Print

Journal of Electronic Imaging

Convex constrained meshes for superpixel segmentations of images
Author(s): Jeremy Forsythe; Vitaliy Kurlin
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We consider the problem of splitting a pixel-based image into convex polygons with vertices at a subpixel resolution. The edges of the resulting polygonal superpixels can have any direction and should adhere well to object boundaries. We introduce a convex constrained mesh that accepts any straight line segments and outputs a complete mesh of convex polygons without small angles and with approximation guarantees for the given lines. Experiments on the Berkeley segmentation dataset BSD500 show that the resulting meshes of polygonal superpixels outperform other polygonal meshes on boundary recall and pixel-based simple linear iterative clustering and superpixels extracted via energy-driven sampling superpixels on undersegmentation errors.

Paper Details

Date Published: 27 September 2017
PDF: 13 pages
J. Electron. Imag. 26(6) 061609 doi: 10.1117/1.JEI.26.6.061609
Published in: Journal of Electronic Imaging Volume 26, Issue 6
Show Author Affiliations
Jeremy Forsythe, Technische Univ. Wien (Austria)
Vitaliy Kurlin, Univ. of Liverpool (United Kingdom)

© SPIE. Terms of Use
Back to Top