Exemplar-based face recognition from video
Krüger, Volker LU
and Zhou, Shaohua
(2002)
7th European Conference on Computer Vision, ECCV 2002
In Lecture Notes in Computer Science
2353.
p.732-746
- Abstract
A new exemplar-based probabilistic approach for face recognition in video sequences is presented. The approach has two stages: First, Exemplars, which are selected representatives from the raw video, are automatically extracted from gallery videos. The exemplars are used to summarize the gallery video information. In the second part, exemplars are then used as centers for probabilistic mixture distributions for the tracking and recognition process. A particle method is used to compute the posteriori probabilities. Probabilistic methods are attractive in this context as they allow a systematic handling of uncertainty and an elegant way for fusing temporal information.Contrary to some previous video-based approaches, our approach is not... (More)
A new exemplar-based probabilistic approach for face recognition in video sequences is presented. The approach has two stages: First, Exemplars, which are selected representatives from the raw video, are automatically extracted from gallery videos. The exemplars are used to summarize the gallery video information. In the second part, exemplars are then used as centers for probabilistic mixture distributions for the tracking and recognition process. A particle method is used to compute the posteriori probabilities. Probabilistic methods are attractive in this context as they allow a systematic handling of uncertainty and an elegant way for fusing temporal information.Contrary to some previous video-based approaches, our approach is not limited to a certain image representation. It rather enhances known ones, such as the PCA, with temporal fusion and uncertainty handling. Experiments demonstrate the effectiveness of each of the two stages. We tested this approach on more than 100 training and testing sequences, with 25 different individuals.
(Less)
- author
- Krüger, Volker
LU
and Zhou, Shaohua
- publishing date
- 2002-01-01
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Exemplar-based learning, Surveillance, Video-based face recognition
- host publication
- Computer Vision - ECCV 2002 : 7th European Conference on Computer Vision, Proceedings - 7th European Conference on Computer Vision, Proceedings
- series title
- Lecture Notes in Computer Science
- editor
- Nielsen, Mads ; Heyden, Anders ; Sparr, Gunnar and Johansen, Peter
- volume
- 2353
- pages
- 15 pages
- publisher
- Springer
- conference name
- 7th European Conference on Computer Vision, ECCV 2002
- conference location
- Copenhagen, Denmark
- conference dates
- 2002-05-28 - 2002-05-31
- external identifiers
-
- scopus:84937563537
- ISSN
- 0302-9743
- 1611-3349
- ISBN
- 978-3-540-43748-2
- 978-3-540-47979-6
- DOI
- 10.1007/3-540-47979-1_49
- language
- English
- LU publication?
- no
- id
- 635254d5-f133-4e87-80c1-170c051c7337
- date added to LUP
- 2019-07-08 21:23:41
- date last changed
- 2024-01-01 15:52:45
@inproceedings{635254d5-f133-4e87-80c1-170c051c7337,
abstract = {{<p>A new exemplar-based probabilistic approach for face recognition in video sequences is presented. The approach has two stages: First, Exemplars, which are selected representatives from the raw video, are automatically extracted from gallery videos. The exemplars are used to summarize the gallery video information. In the second part, exemplars are then used as centers for probabilistic mixture distributions for the tracking and recognition process. A particle method is used to compute the posteriori probabilities. Probabilistic methods are attractive in this context as they allow a systematic handling of uncertainty and an elegant way for fusing temporal information.Contrary to some previous video-based approaches, our approach is not limited to a certain image representation. It rather enhances known ones, such as the PCA, with temporal fusion and uncertainty handling. Experiments demonstrate the effectiveness of each of the two stages. We tested this approach on more than 100 training and testing sequences, with 25 different individuals.</p>}},
author = {{Krüger, Volker and Zhou, Shaohua}},
booktitle = {{Computer Vision - ECCV 2002 : 7th European Conference on Computer Vision, Proceedings}},
editor = {{Nielsen, Mads and Heyden, Anders and Sparr, Gunnar and Johansen, Peter}},
isbn = {{978-3-540-43748-2}},
issn = {{0302-9743}},
keywords = {{Exemplar-based learning; Surveillance; Video-based face recognition}},
language = {{eng}},
month = {{01}},
pages = {{732--746}},
publisher = {{Springer}},
series = {{Lecture Notes in Computer Science}},
title = {{Exemplar-based face recognition from video}},
url = {{http://dx.doi.org/10.1007/3-540-47979-1_49}},
doi = {{10.1007/3-540-47979-1_49}},
volume = {{2353}},
year = {{2002}},
}