ML Anthology

A Parametric Template Method and Its Application to Robust Matching

Koichi Tanaka, Mutsuo Sano, Shuichi Ohara, Masashi Okudaira
CVPR 2000 pp. 1620-1627
doi:10.1109/CVPR.2000.855877 /cvpr/2000/tanaka2000cvpr-parametric/

Abstract

We propose a template-matching method in which a parametric template space is constructed from a given set of template images then quickly matched to a reference image. In this method geometrical changes in an image object due to translation, rotation or scaling, and non-geometrical changes such as illumination variations or individual variation between objects are represented by template images in the parametric template space. The method also provides a subpixel matching scheme that yields a high-precision estimation of the object position. Experiments using real images have confirmed the effectiveness of the method.

CVPR Semantic Scholar

Cite

Text

Tanaka et al. "A Parametric Template Method and Its Application to Robust Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.855877

Markdown

[Tanaka et al. "A Parametric Template Method and Its Application to Robust Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/tanaka2000cvpr-parametric/) doi:10.1109/CVPR.2000.855877

BibTeX

@inproceedings{tanaka2000cvpr-parametric,
  title     = {{A Parametric Template Method and Its Application to Robust Matching}},
  author    = {Tanaka, Koichi and Sano, Mutsuo and Ohara, Shuichi and Okudaira, Masashi},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {1620-1627},
  doi       = {10.1109/CVPR.2000.855877},
  url       = {https://mlanthology.org/cvpr/2000/tanaka2000cvpr-parametric/}
}