Gabor attributes tracking for face verification

Baoxin Li, R. Chellappa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

A method based on sequential importance sampling is proposed for tracking facial features on a grid with Gabor attributes. The motion of facial feature points is modeled as a global 2-D affine transformation (accounting for head motion) plus a local deformation (accounting for residual motion due to inaccuracies in 2-D affine modeling and other factors such as facial expression). Motion of both types is estimated simultaneously by the tracker: global motion is tracked by importance sampling, and residual motion is handled by incorporating local deformation into the measurement likelihood in computing the weight of a sample. While it has other applications in facial analysis, the method is particularly applicable to face verification because of a novel parametrization.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Image Processing
Pages45-48
Number of pages4
Volume1
StatePublished - 2000
Externally publishedYes
EventInternational Conference on Image Processing (ICIP 2000) - Vancouver, BC, Canada
Duration: Sep 10 2000Sep 13 2000

Other

OtherInternational Conference on Image Processing (ICIP 2000)
CountryCanada
CityVancouver, BC
Period9/10/009/13/00

Fingerprint

Importance sampling

ASJC Scopus subject areas

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

Cite this

Li, B., & Chellappa, R. (2000). Gabor attributes tracking for face verification. In IEEE International Conference on Image Processing (Vol. 1, pp. 45-48)

Gabor attributes tracking for face verification. / Li, Baoxin; Chellappa, R.

IEEE International Conference on Image Processing. Vol. 1 2000. p. 45-48.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, B & Chellappa, R 2000, Gabor attributes tracking for face verification. in IEEE International Conference on Image Processing. vol. 1, pp. 45-48, International Conference on Image Processing (ICIP 2000), Vancouver, BC, Canada, 9/10/00.
Li B, Chellappa R. Gabor attributes tracking for face verification. In IEEE International Conference on Image Processing. Vol. 1. 2000. p. 45-48
Li, Baoxin ; Chellappa, R. / Gabor attributes tracking for face verification. IEEE International Conference on Image Processing. Vol. 1 2000. pp. 45-48
@inproceedings{2932bf0bfe154ea0a3ffe84194083ca3,
title = "Gabor attributes tracking for face verification",
abstract = "A method based on sequential importance sampling is proposed for tracking facial features on a grid with Gabor attributes. The motion of facial feature points is modeled as a global 2-D affine transformation (accounting for head motion) plus a local deformation (accounting for residual motion due to inaccuracies in 2-D affine modeling and other factors such as facial expression). Motion of both types is estimated simultaneously by the tracker: global motion is tracked by importance sampling, and residual motion is handled by incorporating local deformation into the measurement likelihood in computing the weight of a sample. While it has other applications in facial analysis, the method is particularly applicable to face verification because of a novel parametrization.",
author = "Baoxin Li and R. Chellappa",
year = "2000",
language = "English (US)",
volume = "1",
pages = "45--48",
booktitle = "IEEE International Conference on Image Processing",

}

TY - GEN

T1 - Gabor attributes tracking for face verification

AU - Li, Baoxin

AU - Chellappa, R.

PY - 2000

Y1 - 2000

N2 - A method based on sequential importance sampling is proposed for tracking facial features on a grid with Gabor attributes. The motion of facial feature points is modeled as a global 2-D affine transformation (accounting for head motion) plus a local deformation (accounting for residual motion due to inaccuracies in 2-D affine modeling and other factors such as facial expression). Motion of both types is estimated simultaneously by the tracker: global motion is tracked by importance sampling, and residual motion is handled by incorporating local deformation into the measurement likelihood in computing the weight of a sample. While it has other applications in facial analysis, the method is particularly applicable to face verification because of a novel parametrization.

AB - A method based on sequential importance sampling is proposed for tracking facial features on a grid with Gabor attributes. The motion of facial feature points is modeled as a global 2-D affine transformation (accounting for head motion) plus a local deformation (accounting for residual motion due to inaccuracies in 2-D affine modeling and other factors such as facial expression). Motion of both types is estimated simultaneously by the tracker: global motion is tracked by importance sampling, and residual motion is handled by incorporating local deformation into the measurement likelihood in computing the weight of a sample. While it has other applications in facial analysis, the method is particularly applicable to face verification because of a novel parametrization.

UR - http://www.scopus.com/inward/record.url?scp=0034442839&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034442839&partnerID=8YFLogxK

M3 - Conference contribution

VL - 1

SP - 45

EP - 48

BT - IEEE International Conference on Image Processing

ER -