ML Anthology

Appearance-Based Keypoint Clustering

Francisco J. Estrada, Pascal Fua, Vincent Lepetit, Sabine Süsstrunk
CVPR 2009 pp. 1279-1286
doi:10.1109/CVPR.2009.5206514 /cvpr/2009/estrada2009cvpr-appearance/

Abstract

We present an algorithm for clustering sets of detected interest points into groups that correspond to visually distinct structure. Through the use of a suitable colour and texture representation, our clustering method is able to identify keypoints that belong to separate objects or background regions. These clusters are then used to constrain the matching of keypoints over pairs of images, resulting in greatly improved matching under difficult conditions. We present a thorough evaluation of each component of the algorithm, and show its usefulness on difficult matching problems.

PDF CVPR Semantic Scholar

Cite

Text

Estrada et al. "Appearance-Based Keypoint Clustering." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009. doi:10.1109/CVPR.2009.5206514

Markdown

[Estrada et al. "Appearance-Based Keypoint Clustering." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009.](https://mlanthology.org/cvpr/2009/estrada2009cvpr-appearance/) doi:10.1109/CVPR.2009.5206514

BibTeX

@inproceedings{estrada2009cvpr-appearance,
  title     = {{Appearance-Based Keypoint Clustering}},
  author    = {Estrada, Francisco J. and Fua, Pascal and Lepetit, Vincent and Süsstrunk, Sabine},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2009},
  pages     = {1279-1286},
  doi       = {10.1109/CVPR.2009.5206514},
  url       = {https://mlanthology.org/cvpr/2009/estrada2009cvpr-appearance/}
}