Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation
Abstract
Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this paper. First, we construct a contour matrix containing all object boundaries in a training set. Second, we decompose the contour matrix into eigencontours via the best rank-M approximation. Third, we represent an object boundary by a linear combination of the M eigencontours. We also incorporate the eigencontours into an instance segmentation framework. Experimental results demonstrate that the proposed eigencontours can represent object boundaries more effectively and more efficiently than existing descriptors in a low-dimensional space. Furthermore, the proposed algorithm yields meaningful performances on instance segmentation datasets.
Cite
Text
Park et al. "Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation." Conference on Computer Vision and Pattern Recognition, 2022. doi:10.1109/CVPR52688.2022.00269Markdown
[Park et al. "Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation." Conference on Computer Vision and Pattern Recognition, 2022.](https://mlanthology.org/cvpr/2022/park2022cvpr-eigencontours/) doi:10.1109/CVPR52688.2022.00269BibTeX
@inproceedings{park2022cvpr-eigencontours,
title = {{Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation}},
author = {Park, Wonhui and Jin, Dongkwon and Kim, Chang-Su},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2022},
pages = {2667-2675},
doi = {10.1109/CVPR52688.2022.00269},
url = {https://mlanthology.org/cvpr/2022/park2022cvpr-eigencontours/}
}