Global Bilateral Symmetry Detection Using Multiscale Mirror Histograms

Mohamed Elawady (1) , Cécile Barat (1) , Christophe Ducottet (1) , Philippe Colantoni (2) , Cecile Barat (1)

1 LHC - Laboratoire Hubert Curien [Saint Etienne]
2 CIEREC (EA 3068) - Centre Interdisciplinaire d'Etudes et de recherche sur l'Expression Contemporaine

In recent years, there has been renewed interest in bilateral symmetry detection in images. It consists in detecting the main bilateral symmetry axis inside artificial or natural images. State-of-the-art methods combine feature point detection, pairwise comparison and voting in Hough-like space. In spite of their good performance, they fail to give reliable results over challenging real-world and artistic images. In this paper, we propose a novel symmetry detection method using multi-scale edge features combined with local orientation histograms. An experimental evaluation is conducted on public datasets plus a new aesthetic-oriented dataset. The results show that our approach outperforms all other concurrent methods.

Keywords: Symmetry Detection; Reflection Symmetry; Edge Features; Pairwise Similarity; Symmetry Histogram

Domains: Computer Science [cs]; Image Processing [eess.IV]

Mohamed Elawady, Cécile Barat, Christophe Ducottet, Philippe Colantoni, Cecile Barat. Global Bilateral Symmetry Detection Using Multiscale Mirror Histograms. 17th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2016) , Oct 2016, Lecce, Italy. pp.14 - 24, ⟨10.1007/978-3-319-48680-2_2⟩. ⟨ujm-01387193v2⟩