ML Anthology

Unsupervised Face Recognition from Image Sequences Based on Clustering with Attraction and Repulsion

Bisser Raytchev, Hiroshi Murase
CVPR 2001 pp. II:25-30
doi:10.1109/CVPR.2001.990920 /cvpr/2001/raytchev2001cvpr-unsupervised/

Abstract

We propose a new method for unsupervised face recognition from time-varying sequences of face images obtained in real-world environments. Two types of forces, attraction and repulsion, operate across the spatio-temporal facial manifolds, to autonomously organize the data without relying on any category-specific information provided in advance. Experiments with real-world data gathered over a period of several months and including both frontal and side-view faces were used to evaluate the method and encouraging results were obtained The proposed method can be used in video surveillance systems or for content-based information retrieval.

CVPR Semantic Scholar

Cite

Text

Raytchev and Murase. "Unsupervised Face Recognition from Image Sequences Based on Clustering with Attraction and Repulsion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.990920

Markdown

[Raytchev and Murase. "Unsupervised Face Recognition from Image Sequences Based on Clustering with Attraction and Repulsion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/raytchev2001cvpr-unsupervised/) doi:10.1109/CVPR.2001.990920

BibTeX

@inproceedings{raytchev2001cvpr-unsupervised,
  title     = {{Unsupervised Face Recognition from Image Sequences Based on Clustering with Attraction and Repulsion}},
  author    = {Raytchev, Bisser and Murase, Hiroshi},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {II:25-30},
  doi       = {10.1109/CVPR.2001.990920},
  url       = {https://mlanthology.org/cvpr/2001/raytchev2001cvpr-unsupervised/}
}