mawady / ColorSymDetect

Wavelet-based Reflection Symmetry Detection via Textural and Color Histograms (ICCV 2017)

Color-based Reflection Symmetry Detection

Winner of ICCV 2017 2D reflection symmetry detection challenge (among participants - conference rank A*)

Funk, Christopher, et al. "2017 ICCV challenge: Detecting symmetry in the wild." Proceedings of the IEEE International Conference on Computer Vision Workshops. 2017.

Users of this software are encouraged to cite the following article:

• Elawady, Mohamed, Christophe Ducottet, Olivier Alata, Cécile Barat, and Philippe Colantoni. "Wavelet-based reflection symmetry detection via textural and color histograms." In Proceedings, ICCV Workshop on Detecting Symmetry in the Wild, Venice, vol. 3, p. 7. 2017.

@inproceedings{elawady2017wavelet,
  title={Wavelet-based reflection symmetry detection via textural and color histograms},
  author={Elawady, Mohamed and Ducottet, Christophe and Alata, Olivier and Barat, Cecile and Colantoni, Philippe},
  booktitle={Proceedings, ICCV Workshop on Detecting Symmetry in the Wild, Venice},
  volume={3},
  pages={7},
  year={2017}
}

You can download the paper here!

The sample photos are kindly provided by Aesthetic Visual Analysis (AVA) dataset.

Contact: Mohamed Elawady (mohamed [dot] elawady [at] univ-st-etienne [dot] fr)

FILE:

• main.m - code for computer symmetry on an image and display the candidates' info (axes, voting representation)
• symBilOurCentLogGaborHSV.m - code for main function to compute symmetry on an image