A convolutional approach to reflection symmetry

TL;DR

This paper introduces a convolutional method for detecting reflection symmetry in 2D images using complex wavelet convolutions, offering computational advantages and improved accuracy over previous methods, especially when object sizes are known.

Contribution

It proposes a novel, parameter-centered convolutional approach that simplifies symmetry detection and outperforms existing algorithms on benchmark datasets.

Findings

Outperforms the best algorithm on the CVPR 2013 Symmetry Detection Competition Database.

Provides computational advantages for known object sizes.

Includes code and a new database for 2D symmetry detection.

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. Code and a new database for 2D symmetry detection is available.