English

Shape Characterization via Boundary Distortion

Computer Vision and Pattern Recognition 2013-02-26 v1

Abstract

In this paper, we derive new shape descriptors based on a directional characterization. The main idea is to study the behavior of the shape neighborhood under family of transformations. We obtain a description invariant with respect to rotation, reflection, translation and scaling. A well-defined metric is then proposed on the associated feature space. We show the continuity of this metric. Some results on shape retrieval are provided on two databases to show the accuracy of the proposed shape metric.

Keywords

Cite

@article{arxiv.1302.5957,
  title  = {Shape Characterization via Boundary Distortion},
  author = {Xavier Descombes and Serguei Komech},
  journal= {arXiv preprint arXiv:1302.5957},
  year   = {2013}
}

Comments

14 pages, 5 figures

R2 v1 2026-06-21T23:31:49.911Z