Facial component extraction and face recognition with support vector machines

Dihua Xi, Igor T. Podolak, Seong Whan Lee

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

22 Citations (Scopus)

Abstract

A method for face recognition is proposed which uses a two-step approach: first, a number of facial components are found, which are then glued together, and the resulting face vector is recognized as representing one of the possible persons. During the extraction step, a wavelet statistics subsystem provides the possible locations of the eyes and mouth, which are used by a support vector machine (SVM) subsystem to extract the facial components. The use of a wavelet statistics subsystem speeds up the recognition process markedly. Both the feature detection SVMs and the wavelet statistics subsystem are trained on a small number of actual images with marked features. Afterwards, a large number of face vectors are constructed, which are then classified with another set of SVM machines.

Original languageEnglish
Title of host publicationProceedings - 5th IEEE International Conference on Automatic Face Gesture Recognition, FGR 2002
PublisherIEEE Computer Society
Pages83-88
Number of pages6
ISBN (Print)0769516025, 9780769516028
DOIs
Publication statusPublished - 2002 Jan 1
Event5th IEEE International Conference on Automatic Face Gesture Recognition, FGR 2002 - Washington, DC, United States
Duration: 2002 May 202002 May 21

Other

Other5th IEEE International Conference on Automatic Face Gesture Recognition, FGR 2002
CountryUnited States
CityWashington, DC
Period02/5/2002/5/21

Fingerprint

Face recognition
Support vector machines
Statistics

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Xi, D., Podolak, I. T., & Lee, S. W. (2002). Facial component extraction and face recognition with support vector machines. In Proceedings - 5th IEEE International Conference on Automatic Face Gesture Recognition, FGR 2002 (pp. 83-88). [1004136] IEEE Computer Society. https://doi.org/10.1109/AFGR.2002.1004136

Facial component extraction and face recognition with support vector machines. / Xi, Dihua; Podolak, Igor T.; Lee, Seong Whan.

Proceedings - 5th IEEE International Conference on Automatic Face Gesture Recognition, FGR 2002. IEEE Computer Society, 2002. p. 83-88 1004136.

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

Xi, D, Podolak, IT & Lee, SW 2002, Facial component extraction and face recognition with support vector machines. in Proceedings - 5th IEEE International Conference on Automatic Face Gesture Recognition, FGR 2002., 1004136, IEEE Computer Society, pp. 83-88, 5th IEEE International Conference on Automatic Face Gesture Recognition, FGR 2002, Washington, DC, United States, 02/5/20. https://doi.org/10.1109/AFGR.2002.1004136
Xi D, Podolak IT, Lee SW. Facial component extraction and face recognition with support vector machines. In Proceedings - 5th IEEE International Conference on Automatic Face Gesture Recognition, FGR 2002. IEEE Computer Society. 2002. p. 83-88. 1004136 https://doi.org/10.1109/AFGR.2002.1004136
Xi, Dihua ; Podolak, Igor T. ; Lee, Seong Whan. / Facial component extraction and face recognition with support vector machines. Proceedings - 5th IEEE International Conference on Automatic Face Gesture Recognition, FGR 2002. IEEE Computer Society, 2002. pp. 83-88
@inproceedings{148243a1db454014bfc156c8e6e7fd4c,
title = "Facial component extraction and face recognition with support vector machines",
abstract = "A method for face recognition is proposed which uses a two-step approach: first, a number of facial components are found, which are then glued together, and the resulting face vector is recognized as representing one of the possible persons. During the extraction step, a wavelet statistics subsystem provides the possible locations of the eyes and mouth, which are used by a support vector machine (SVM) subsystem to extract the facial components. The use of a wavelet statistics subsystem speeds up the recognition process markedly. Both the feature detection SVMs and the wavelet statistics subsystem are trained on a small number of actual images with marked features. Afterwards, a large number of face vectors are constructed, which are then classified with another set of SVM machines.",
author = "Dihua Xi and Podolak, {Igor T.} and Lee, {Seong Whan}",
year = "2002",
month = "1",
day = "1",
doi = "10.1109/AFGR.2002.1004136",
language = "English",
isbn = "0769516025",
pages = "83--88",
booktitle = "Proceedings - 5th IEEE International Conference on Automatic Face Gesture Recognition, FGR 2002",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Facial component extraction and face recognition with support vector machines

AU - Xi, Dihua

AU - Podolak, Igor T.

AU - Lee, Seong Whan

PY - 2002/1/1

Y1 - 2002/1/1

N2 - A method for face recognition is proposed which uses a two-step approach: first, a number of facial components are found, which are then glued together, and the resulting face vector is recognized as representing one of the possible persons. During the extraction step, a wavelet statistics subsystem provides the possible locations of the eyes and mouth, which are used by a support vector machine (SVM) subsystem to extract the facial components. The use of a wavelet statistics subsystem speeds up the recognition process markedly. Both the feature detection SVMs and the wavelet statistics subsystem are trained on a small number of actual images with marked features. Afterwards, a large number of face vectors are constructed, which are then classified with another set of SVM machines.

AB - A method for face recognition is proposed which uses a two-step approach: first, a number of facial components are found, which are then glued together, and the resulting face vector is recognized as representing one of the possible persons. During the extraction step, a wavelet statistics subsystem provides the possible locations of the eyes and mouth, which are used by a support vector machine (SVM) subsystem to extract the facial components. The use of a wavelet statistics subsystem speeds up the recognition process markedly. Both the feature detection SVMs and the wavelet statistics subsystem are trained on a small number of actual images with marked features. Afterwards, a large number of face vectors are constructed, which are then classified with another set of SVM machines.

UR - http://www.scopus.com/inward/record.url?scp=17244372003&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17244372003&partnerID=8YFLogxK

U2 - 10.1109/AFGR.2002.1004136

DO - 10.1109/AFGR.2002.1004136

M3 - Conference contribution

AN - SCOPUS:17244372003

SN - 0769516025

SN - 9780769516028

SP - 83

EP - 88

BT - Proceedings - 5th IEEE International Conference on Automatic Face Gesture Recognition, FGR 2002

PB - IEEE Computer Society

ER -