Probabilistic recognition of human faces from video

Rama Chellappa; Volker Krüger; Shaohua Zhou

Probabilistic recognition of human faces from video

Rama Chellappa
, Volker Krüger
, Shaohua Zhou

Research output: Contribution to conference › Paper › peer-review

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.

Original language	English (US)
Pages	I/41-I/44
State	Published - 2002
Externally published	Yes
Event	International Conference on Image Processing (ICIP'02) - Rochester, NY, United States Duration: Sep 22 2002 → Sep 25 2002

Other

Other	International Conference on Image Processing (ICIP'02)
Country/Territory	United States
City	Rochester, NY
Period	9/22/02 → 9/25/02

ASJC Scopus subject areas

Hardware and Architecture
Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Cite this

@conference{a82c80b27a984460b7b35b9ffa794fec,

title = "Probabilistic recognition of human faces from video",

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.",

author = "Rama Chellappa and Volker Kr{\"u}ger and Shaohua Zhou",

note = "Funding Information: This work was completed with the support of the DARPA HumanID Grant N00014-00-1-0908. All correspondences are addressed to [email protected]. Tel: 301-405-4526. Fax: 301-314-9115. Krueger was affiliated with CfAR. He is now at the Aalborg University, Denmark. ; International Conference on Image Processing (ICIP'02) ; Conference date: 22-09-2002 Through 25-09-2002",

year = "2002",

language = "English (US)",

pages = "I/41--I/44",

}

TY - CONF

T1 - Probabilistic recognition of human faces from video

AU - Chellappa, Rama

AU - Krüger, Volker

AU - Zhou, Shaohua

N1 - Funding Information: This work was completed with the support of the DARPA HumanID Grant N00014-00-1-0908. All correspondences are addressed to [email protected]. Tel: 301-405-4526. Fax: 301-314-9115. Krueger was affiliated with CfAR. He is now at the Aalborg University, Denmark.

PY - 2002

Y1 - 2002

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/0036451204

UR - https://www.scopus.com/pages/publications/0036451204#tab=citedBy

M3 - Paper

AN - SCOPUS:0036451204

SP - I/41-I/44

T2 - International Conference on Image Processing (ICIP'02)

Y2 - 22 September 2002 through 25 September 2002

ER -

Probabilistic recognition of human faces from video

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this