Probabilistic recognition of human faces from video
Chellappa, Rama ; Krüger, Volker LU
and Zhou, Shaohua
(2002)
International Conference on Image Processing (ICIP'02)
p.41-44
- Abstract
Most present face recognition approaches recognize faces based on still images. In this paper, we present a novel approach to recognize faces in video. In that scenario, the face gallery may consist of still images or may be derived from a videos. For evidence integration we use classical Bayesian propagation over time and compute the posterior distribution using sequential importance sampling. The probabilistic approach allows us to handle uncertainties in a systematic manner. Experimental results using videos collected by NIST/USF and CMU illustrate the effectiveness of this approach in both still-to-video and video-to-video scenarios with appropriate model choices.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/12d88409-2134-4579-8d33-507a63a3c21e
- author
- Chellappa, Rama
; Krüger, Volker
LU
and Zhou, Shaohua
- publishing date
- 2002-01-01
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Proceedings. International Conference on Image Processing
- pages
- 41 - 44
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- International Conference on Image Processing (ICIP'02)
- conference location
- Rochester, NY, United States
- conference dates
- 2002-09-22 - 2002-09-25
- external identifiers
-
- scopus:0036451204
- ISBN
- 0-7803-7622-6
- DOI
- 10.1109/ICIP.2002.1037954
- language
- English
- LU publication?
- no
- id
- 12d88409-2134-4579-8d33-507a63a3c21e
- date added to LUP
- 2019-07-08 21:27:39
- date last changed
- 2025-04-04 14:12:47
@inproceedings{12d88409-2134-4579-8d33-507a63a3c21e,
abstract = {{<p>Most present face recognition approaches recognize faces based on still images. In this paper, we present a novel approach to recognize faces in video. In that scenario, the face gallery may consist of still images or may be derived from a videos. For evidence integration we use classical Bayesian propagation over time and compute the posterior distribution using sequential importance sampling. The probabilistic approach allows us to handle uncertainties in a systematic manner. Experimental results using videos collected by NIST/USF and CMU illustrate the effectiveness of this approach in both still-to-video and video-to-video scenarios with appropriate model choices.</p>}},
author = {{Chellappa, Rama and Krüger, Volker and Zhou, Shaohua}},
booktitle = {{Proceedings. International Conference on Image Processing}},
isbn = {{0-7803-7622-6}},
language = {{eng}},
month = {{01}},
pages = {{41--44}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
title = {{Probabilistic recognition of human faces from video}},
url = {{http://dx.doi.org/10.1109/ICIP.2002.1037954}},
doi = {{10.1109/ICIP.2002.1037954}},
year = {{2002}},
}