Wavelet-based Reflection Symmetry Detection via Textural and Color Histograms

Mohamed Elawady 1 Christophe Ducottet 1 Olivier Alata 1 Cecile Barat 1 Philippe Colantoni 2
1 LHC - Laboratoire Hubert Curien [Saint Etienne]
2 C2RMF - Centre de recherche et de restauration des musées de France
Abstract : Symmetry is one of the significant visual properties inside an image plane, to identify the geometrically balanced structures through real-world objects. Existing symmetry detection methods rely on descriptors of the local image features and their neighborhood behavior, resulting incomplete symmetrical axis candidates to discover the mirror similarities on a global scale. In this paper, we propose a new reflection symmetry detection scheme, based on a reliable edge-based feature extraction using Log-Gabor filters , plus an efficient voting scheme parameterized by their corresponding textural and color neighborhood information. Experimental evaluation on four single-case and three multiple-case symmetry detection datasets validates the superior achievement of the proposed work to find global symmetries inside an image.
Document type :
Conference papers
Complete list of metadatas

Cited literature [29 references]  Display  Hide  Download
https://hal-ujm.archives-ouvertes.fr/ujm-01637175
Contributor : Christophe Ducottet <>
Submitted on : Monday, November 20, 2017 - 1:12:52 PM
Last modification on : Sunday, July 28, 2019 - 6:04:02 PM
Long-term archiving on : Wednesday, February 21, 2018 - 12:22:41 PM

File

iccv-paper-wavelet.pdf
Files produced by the author(s)

Identifiers

Collections

UNIV-ST-ETIENNE | IOGS | PARISTECH | UNIV-PARIS-SACLAY

Citation

Mohamed Elawady, Christophe Ducottet, Olivier Alata, Cecile Barat, Philippe Colantoni. Wavelet-based Reflection Symmetry Detection via Textural and Color Histograms. ICCV 2017, IEEE International Conference on Computer Vision Workshop Detecting Symmetry in the Wild, Oct 2017, Venice, Italy. ⟨10.1109/ICCVW.2017.202⟩. ⟨ujm-01637175⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

144

Files downloads

332

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD