A convolutional approach to reflection symmetry

Marcelo Cicconet, Vighnesh Birodkar, Mads Lund, Michael Werman, Davi Geiger

Research output: Contribution to journalArticle

Abstract

We present a convolutional approach to reflection symmetry detection in 2D. Our model, built on the products of complex-valued wavelet convolutions, simplifies previous edge-based pairwise methods. Being parameter-centered, as opposed to feature-centered, it has certain computational advantages when the object sizes are known a priori, as demonstrated in an ellipse detection application. The method outperforms the best-performing algorithm on the CVPR 2013 Symmetry Detection Competition Database in the single-symmetry case. We release code and a new, larger image database.

Original languageEnglish (US)
Pages (from-to)44-50
Number of pages7
JournalPattern Recognition Letters
Volume95
DOIs
StatePublished - Aug 1 2017

Fingerprint

Convolution

Keywords

  • Mirror symmetry
  • Reflection symmetry

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

A convolutional approach to reflection symmetry. / Cicconet, Marcelo; Birodkar, Vighnesh; Lund, Mads; Werman, Michael; Geiger, Davi.

In: Pattern Recognition Letters, Vol. 95, 01.08.2017, p. 44-50.

Research output: Contribution to journalArticle

Cicconet, Marcelo ; Birodkar, Vighnesh ; Lund, Mads ; Werman, Michael ; Geiger, Davi. / A convolutional approach to reflection symmetry. In: Pattern Recognition Letters. 2017 ; Vol. 95. pp. 44-50.
@article{04d21a2688f440d4813a269b841c2eb2,
title = "A convolutional approach to reflection symmetry",
abstract = "We present a convolutional approach to reflection symmetry detection in 2D. Our model, built on the products of complex-valued wavelet convolutions, simplifies previous edge-based pairwise methods. Being parameter-centered, as opposed to feature-centered, it has certain computational advantages when the object sizes are known a priori, as demonstrated in an ellipse detection application. The method outperforms the best-performing algorithm on the CVPR 2013 Symmetry Detection Competition Database in the single-symmetry case. We release code and a new, larger image database.",
keywords = "Mirror symmetry, Reflection symmetry",
author = "Marcelo Cicconet and Vighnesh Birodkar and Mads Lund and Michael Werman and Davi Geiger",
year = "2017",
month = "8",
day = "1",
doi = "10.1016/j.patrec.2017.03.022",
language = "English (US)",
volume = "95",
pages = "44--50",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",

}

TY - JOUR

T1 - A convolutional approach to reflection symmetry

AU - Cicconet, Marcelo

AU - Birodkar, Vighnesh

AU - Lund, Mads

AU - Werman, Michael

AU - Geiger, Davi

PY - 2017/8/1

Y1 - 2017/8/1

N2 - We present a convolutional approach to reflection symmetry detection in 2D. Our model, built on the products of complex-valued wavelet convolutions, simplifies previous edge-based pairwise methods. Being parameter-centered, as opposed to feature-centered, it has certain computational advantages when the object sizes are known a priori, as demonstrated in an ellipse detection application. The method outperforms the best-performing algorithm on the CVPR 2013 Symmetry Detection Competition Database in the single-symmetry case. We release code and a new, larger image database.

AB - We present a convolutional approach to reflection symmetry detection in 2D. Our model, built on the products of complex-valued wavelet convolutions, simplifies previous edge-based pairwise methods. Being parameter-centered, as opposed to feature-centered, it has certain computational advantages when the object sizes are known a priori, as demonstrated in an ellipse detection application. The method outperforms the best-performing algorithm on the CVPR 2013 Symmetry Detection Competition Database in the single-symmetry case. We release code and a new, larger image database.

KW - Mirror symmetry

KW - Reflection symmetry

UR - http://www.scopus.com/inward/record.url?scp=85020286133&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020286133&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2017.03.022

DO - 10.1016/j.patrec.2017.03.022

M3 - Article

VL - 95

SP - 44

EP - 50

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

ER -