Resolution-independent superpixels based on convex constrained meshes without small angles

Jeremy Forsythe, Vitaliy Kurlin, Andrew Fitzgibbon
Resolution-independent superpixels based on convex constrained meshes without small angles
Lecture Notes in Computer Science (LNCS), 10072:223-233, December 2016. [paper] [slides]

Information

Abstract

The over-segmentation problem for images is studied in the new resolution-independent formulation when a large image is approximated by a small number of convex polygons with straight edges at subpixel precision. These polygonal superpixels are obtained by refining and extending subpixel edge segments to a full mesh of convex polygons without small angles and with approximation guarantees. Another novelty is the objective error difference between an original pixel-based image and the reconstructed image with a best constant color over each superpixel, which does not need human segmentations. The experiments on images from the Berkeley Segmentation Database show that new meshes are smaller and provide better approximations than the state-of-the-art.

Additional Files and Images

Additional images and videos

image: null image: null

Additional files

paper: null paper: null

Weblinks

No further information available.

BibTeX

@article{forsythe-2016-ccm,
  title =      "Resolution-independent superpixels based on convex
               constrained meshes without small angles",
  author =     "Jeremy Forsythe and Vitaliy Kurlin and Andrew Fitzgibbon",
  year =       "2016",
  abstract =   "The over-segmentation problem for images is studied in the
               new resolution-independent formulation when a large image is
               approximated by a small number of convex polygons with
               straight edges at subpixel precision. These polygonal
               superpixels are obtained by refining and extending subpixel
               edge segments to a full mesh of convex polygons without
               small angles and with approximation guarantees. Another
               novelty is the objective error difference between an
               original pixel-based image and the reconstructed image with
               a best constant color over each superpixel, which does not
               need human segmentations. The experiments on images from the
               Berkeley Segmentation Database show that new meshes are
               smaller and provide better approximations than the
               state-of-the-art.",
  month =      dec,
  issn =       "0302-9743",
  journal =    "Lecture Notes in Computer Science (LNCS)",
  volume =     "10072",
  pages =      "223--233",
  keywords =   "superpixels, polygonal mesh, Delaunay triangulation,
               constrained triangulation, edge detection",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2016/forsythe-2016-ccm/",
}