InnerSpec: Technical Report
Abstract
In this report we describe “InnerSpec”, an approach for symmetric object detection that is based both on the com- putation of a symmetry measure for each pixel and on gra- dient information analysis. The symmetry value is obtained as the energy balance of the even-odd decomposition of an oriented square patch with respect to its central axis. Such an operation is akin to the computation of a row-wise con- volution in the midpoint. The candidate symmetry axes are then identified through the localization of peaks along the direction perpendicular to each considered angle. These axes are finally evaluated by computing the image gradient in their neighborhood, in particular checking whether the gradient information displays specular characteristics.
Cite
Text
Guerrini et al. "InnerSpec: Technical Report." IEEE/CVF International Conference on Computer Vision Workshops, 2017. doi:10.1109/ICCVW.2017.209Markdown
[Guerrini et al. "InnerSpec: Technical Report." IEEE/CVF International Conference on Computer Vision Workshops, 2017.](https://mlanthology.org/iccvw/2017/guerrini2017iccvw-innerspec/) doi:10.1109/ICCVW.2017.209BibTeX
@inproceedings{guerrini2017iccvw-innerspec,
title = {{InnerSpec: Technical Report}},
author = {Guerrini, Fabrizio and Gnutti, Alessandro and Leonardi, Riccardo},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2017},
pages = {1774-1778},
doi = {10.1109/ICCVW.2017.209},
url = {https://mlanthology.org/iccvw/2017/guerrini2017iccvw-innerspec/}
}