ML Anthology

Detection of Mirror-Symmetric Image Patches

Viorica Patraucean, Rafael Grompone von Gioi, Maks Ovsjanikov
CVPRW 2013 pp. 211-216
doi:10.1109/CVPRW.2013.38 /cvprw/2013/patraucean2013cvprw-detection/

Abstract

We propose a novel approach for detecting partial re-flectional symmetry in images. Our method consists of two principal stages: candidate selection and validation. In the first step, candidates for mirror-symmetric patches are iden-tified using an existing heuristic procedure based on Hough voting. The candidates are then validated using a princi-pled statistical procedure inspired from the a contrario the-ory, which minimizes the number of false positives. Our algorithm uses integral image properties to enhance the ex-ecution time. 1.

PDF CVPRW Semantic Scholar

Cite

Text

Patraucean et al. "Detection of Mirror-Symmetric Image Patches." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2013. doi:10.1109/CVPRW.2013.38

Markdown

[Patraucean et al. "Detection of Mirror-Symmetric Image Patches." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2013.](https://mlanthology.org/cvprw/2013/patraucean2013cvprw-detection/) doi:10.1109/CVPRW.2013.38

BibTeX

@inproceedings{patraucean2013cvprw-detection,
  title     = {{Detection of Mirror-Symmetric Image Patches}},
  author    = {Patraucean, Viorica and von Gioi, Rafael Grompone and Ovsjanikov, Maks},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2013},
  pages     = {211-216},
  doi       = {10.1109/CVPRW.2013.38},
  url       = {https://mlanthology.org/cvprw/2013/patraucean2013cvprw-detection/}
}