Convex constrained meshes for superpixel segmentations of images

Forsythe, Jeremy and Kurlin, Vitaliy ORCID: 0000-0001-5328-5351 (2017) Convex constrained meshes for superpixel segmentations of images. JOURNAL OF ELECTRONIC IMAGING, 26 (6). p. 1.

	Text convex-constrained-meshes-final.pdf - Author Accepted Manuscript Download (6MB)
	Text CCM-superpixels-modified.pdf - Author Accepted Manuscript Download (7MB)

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.

Item Type:	Article
Uncontrolled Keywords:	superpixel over-segmentation, line-segment detection, convex polygonal mesh, constrained triangulation
Depositing User:	Symplectic Admin
Date Deposited:	27 Jun 2018 06:19
Last Modified:	14 Mar 2024 17:32
DOI:	10.1117/1.JEI.26.6.061609
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3020054

Available Versions of this Item

• Convex constrained meshes for superpixel segmentations of images. (deposited 11 Sep 2017 06:26)
  • Convex constrained meshes for superpixel segmentations of images. (deposited 27 Jun 2018 06:19) [Currently Displayed]