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

Keywords

  • Mirror symmetry
  • Reflection symmetry

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'A convolutional approach to reflection symmetry'. Together they form a unique fingerprint.

Cite this