Comparison of face matching techniques under pose variation

B. Kroon, A. Hanjalic, Sabri Boughorbel

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

5 Citations (Scopus)

Abstract

The ability to match faces in video is a crucial component for many multimedia applications such as searching and recognizing people in semantic video browsing, surveillance and home video management systems. Unfortunately, most face matching methods were designed for and tested on frontal face images only, which does not comply with the professional and home video scenarios. In video, faces appear at different poses and scales, and the image quality may vary as well. In this paper we analyzed to what extent well-known face matching methods are suitable for matching faces in video. We performed a comparison between the local method Elastic Bunch Graph Matching, the global approaches principle component analysis (PCA) and PCA with linear discriminant analysis (PCA+LDA). The outcome of this study is that while in cases of small face pose variations Elastic Bunch Graph Matching works slightly better, for large face pose variations the global methods provide better performance.

Original languageEnglish
Title of host publicationProceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007
Pages272-279
Number of pages8
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event6th ACM International Conference on Image and Video Retrieval, CIVR 2007 - Amsterdam, Netherlands
Duration: 9 Jul 200711 Jul 2007

Other

Other6th ACM International Conference on Image and Video Retrieval, CIVR 2007
CountryNetherlands
CityAmsterdam
Period9/7/0711/7/07

Fingerprint

Discriminant analysis
Image quality
Semantics

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science(all)

Cite this

Kroon, B., Hanjalic, A., & Boughorbel, S. (2007). Comparison of face matching techniques under pose variation. In Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007 (pp. 272-279) https://doi.org/10.1145/1282280.1282323

Comparison of face matching techniques under pose variation. / Kroon, B.; Hanjalic, A.; Boughorbel, Sabri.

Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007. 2007. p. 272-279.

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

Kroon, B, Hanjalic, A & Boughorbel, S 2007, Comparison of face matching techniques under pose variation. in Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007. pp. 272-279, 6th ACM International Conference on Image and Video Retrieval, CIVR 2007, Amsterdam, Netherlands, 9/7/07. https://doi.org/10.1145/1282280.1282323
Kroon B, Hanjalic A, Boughorbel S. Comparison of face matching techniques under pose variation. In Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007. 2007. p. 272-279 https://doi.org/10.1145/1282280.1282323
Kroon, B. ; Hanjalic, A. ; Boughorbel, Sabri. / Comparison of face matching techniques under pose variation. Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007. 2007. pp. 272-279
@inproceedings{f677d8cbd2474740b281715cf6fb98c9,
title = "Comparison of face matching techniques under pose variation",
abstract = "The ability to match faces in video is a crucial component for many multimedia applications such as searching and recognizing people in semantic video browsing, surveillance and home video management systems. Unfortunately, most face matching methods were designed for and tested on frontal face images only, which does not comply with the professional and home video scenarios. In video, faces appear at different poses and scales, and the image quality may vary as well. In this paper we analyzed to what extent well-known face matching methods are suitable for matching faces in video. We performed a comparison between the local method Elastic Bunch Graph Matching, the global approaches principle component analysis (PCA) and PCA with linear discriminant analysis (PCA+LDA). The outcome of this study is that while in cases of small face pose variations Elastic Bunch Graph Matching works slightly better, for large face pose variations the global methods provide better performance.",
author = "B. Kroon and A. Hanjalic and Sabri Boughorbel",
year = "2007",
doi = "10.1145/1282280.1282323",
language = "English",
isbn = "1595937331",
pages = "272--279",
booktitle = "Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007",

}

TY - GEN

T1 - Comparison of face matching techniques under pose variation

AU - Kroon, B.

AU - Hanjalic, A.

AU - Boughorbel, Sabri

PY - 2007

Y1 - 2007

N2 - The ability to match faces in video is a crucial component for many multimedia applications such as searching and recognizing people in semantic video browsing, surveillance and home video management systems. Unfortunately, most face matching methods were designed for and tested on frontal face images only, which does not comply with the professional and home video scenarios. In video, faces appear at different poses and scales, and the image quality may vary as well. In this paper we analyzed to what extent well-known face matching methods are suitable for matching faces in video. We performed a comparison between the local method Elastic Bunch Graph Matching, the global approaches principle component analysis (PCA) and PCA with linear discriminant analysis (PCA+LDA). The outcome of this study is that while in cases of small face pose variations Elastic Bunch Graph Matching works slightly better, for large face pose variations the global methods provide better performance.

AB - The ability to match faces in video is a crucial component for many multimedia applications such as searching and recognizing people in semantic video browsing, surveillance and home video management systems. Unfortunately, most face matching methods were designed for and tested on frontal face images only, which does not comply with the professional and home video scenarios. In video, faces appear at different poses and scales, and the image quality may vary as well. In this paper we analyzed to what extent well-known face matching methods are suitable for matching faces in video. We performed a comparison between the local method Elastic Bunch Graph Matching, the global approaches principle component analysis (PCA) and PCA with linear discriminant analysis (PCA+LDA). The outcome of this study is that while in cases of small face pose variations Elastic Bunch Graph Matching works slightly better, for large face pose variations the global methods provide better performance.

UR - http://www.scopus.com/inward/record.url?scp=36849037968&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36849037968&partnerID=8YFLogxK

U2 - 10.1145/1282280.1282323

DO - 10.1145/1282280.1282323

M3 - Conference contribution

SN - 1595937331

SN - 9781595937339

SP - 272

EP - 279

BT - Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007

ER -