ML Anthology

Robust Topological Features for Deformation Invariant Image Matching

Edgar J. Lobaton, Ramanarayan Vasudevan, Ron Alterovitz, Ruzena Bajcsy
ICCV 2011 pp. 2516-2523
doi:10.1109/ICCV.2011.6126538 /iccv/2011/lobaton2011iccv-robust/

Abstract

Local photometric descriptors are a crucial low level component of numerous computer vision algorithms. In practice, these descriptors are constructed to be invariant to a class of transformations. However, the development of a descriptor that is simultaneously robust to noise and invariant under general deformation has proven difficult. In this paper, we introduce the Topological-Attributed Relational Graph (T-ARG), a new local photometric descriptor constructed from homology that is provably invariant to locally bounded deformation. This new robust topological descriptor is backed by a formal mathematical framework. We apply T-ARG to a set of benchmark images to evaluate its performance. Results indicate that T-ARG significantly outperforms traditional descriptors for noisy, deforming images.

PDF ICCV Semantic Scholar

Cite

Text

Lobaton et al. "Robust Topological Features for Deformation Invariant Image Matching." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126538

Markdown

[Lobaton et al. "Robust Topological Features for Deformation Invariant Image Matching." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/lobaton2011iccv-robust/) doi:10.1109/ICCV.2011.6126538

BibTeX

@inproceedings{lobaton2011iccv-robust,
  title     = {{Robust Topological Features for Deformation Invariant Image Matching}},
  author    = {Lobaton, Edgar J. and Vasudevan, Ramanarayan and Alterovitz, Ron and Bajcsy, Ruzena},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2011},
  pages     = {2516-2523},
  doi       = {10.1109/ICCV.2011.6126538},
  url       = {https://mlanthology.org/iccv/2011/lobaton2011iccv-robust/}
}