Automatic face alignment by maximizing similarity score

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

4 Citations (Scopus)
54 Downloads (Pure)

Abstract

Accurate face registration is of vital importance to the performance of a face recognition algorithm. We propose a face registration method which searches for the optimal alignment by maximizing the score of a face recognition algorithm. In this paper we investigate the practical usability of our face registration method. Experiments show that our registration method achieves better results in face verification than the landmark based registration method. We even obtain face verification results which are similar to results obtained using landmark based registration with manually located eyes, nose and mouth as landmarks. The performance of the method is tested on the FRGCv1 database using images taken under both controlled and uncontrolled conditions.
Original languageEnglish
Title of host publicationProceedings of the 7th International Workshop on Pattern Recognition in Information Systems
EditorsA. Fred, A.K. Jain
PublisherINSTICC PRESS
Pages221-230
Number of pages10
ISBN (Print)978-972-8865-93-1
DOIs
Publication statusPublished - 12 Jun 2007

Fingerprint

Face recognition
Experiments

Keywords

  • SCS-Safety
  • Face recognition
  • face registration
  • Alignment
  • Similarity score

Cite this

Boom, B., Spreeuwers, L., & Veldhuis, R. (2007). Automatic face alignment by maximizing similarity score. In A. Fred, & A. K. Jain (Eds.), Proceedings of the 7th International Workshop on Pattern Recognition in Information Systems (pp. 221-230). INSTICC PRESS. https://doi.org/10.5220/0002427602210230
Boom, Bas ; Spreeuwers, Luuk ; Veldhuis, Raymond. / Automatic face alignment by maximizing similarity score. Proceedings of the 7th International Workshop on Pattern Recognition in Information Systems. editor / A. Fred ; A.K. Jain. INSTICC PRESS, 2007. pp. 221-230
@inproceedings{bd621476d6c44b6fa5fea5316450d1cc,
title = "Automatic face alignment by maximizing similarity score",
abstract = "Accurate face registration is of vital importance to the performance of a face recognition algorithm. We propose a face registration method which searches for the optimal alignment by maximizing the score of a face recognition algorithm. In this paper we investigate the practical usability of our face registration method. Experiments show that our registration method achieves better results in face verification than the landmark based registration method. We even obtain face verification results which are similar to results obtained using landmark based registration with manually located eyes, nose and mouth as landmarks. The performance of the method is tested on the FRGCv1 database using images taken under both controlled and uncontrolled conditions.",
keywords = "SCS-Safety, Face recognition, face registration, Alignment, Similarity score",
author = "Bas Boom and Luuk Spreeuwers and Raymond Veldhuis",
note = "SAS 030-07",
year = "2007",
month = "6",
day = "12",
doi = "10.5220/0002427602210230",
language = "English",
isbn = "978-972-8865-93-1",
pages = "221--230",
editor = "A. Fred and A.K. Jain",
booktitle = "Proceedings of the 7th International Workshop on Pattern Recognition in Information Systems",
publisher = "INSTICC PRESS",

}

Boom, B, Spreeuwers, L & Veldhuis, R 2007, Automatic face alignment by maximizing similarity score. in A Fred & AK Jain (eds), Proceedings of the 7th International Workshop on Pattern Recognition in Information Systems. INSTICC PRESS, pp. 221-230. https://doi.org/10.5220/0002427602210230

Automatic face alignment by maximizing similarity score. / Boom, Bas; Spreeuwers, Luuk; Veldhuis, Raymond.

Proceedings of the 7th International Workshop on Pattern Recognition in Information Systems. ed. / A. Fred; A.K. Jain. INSTICC PRESS, 2007. p. 221-230.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Automatic face alignment by maximizing similarity score

AU - Boom, Bas

AU - Spreeuwers, Luuk

AU - Veldhuis, Raymond

N1 - SAS 030-07

PY - 2007/6/12

Y1 - 2007/6/12

N2 - Accurate face registration is of vital importance to the performance of a face recognition algorithm. We propose a face registration method which searches for the optimal alignment by maximizing the score of a face recognition algorithm. In this paper we investigate the practical usability of our face registration method. Experiments show that our registration method achieves better results in face verification than the landmark based registration method. We even obtain face verification results which are similar to results obtained using landmark based registration with manually located eyes, nose and mouth as landmarks. The performance of the method is tested on the FRGCv1 database using images taken under both controlled and uncontrolled conditions.

AB - Accurate face registration is of vital importance to the performance of a face recognition algorithm. We propose a face registration method which searches for the optimal alignment by maximizing the score of a face recognition algorithm. In this paper we investigate the practical usability of our face registration method. Experiments show that our registration method achieves better results in face verification than the landmark based registration method. We even obtain face verification results which are similar to results obtained using landmark based registration with manually located eyes, nose and mouth as landmarks. The performance of the method is tested on the FRGCv1 database using images taken under both controlled and uncontrolled conditions.

KW - SCS-Safety

KW - Face recognition

KW - face registration

KW - Alignment

KW - Similarity score

U2 - 10.5220/0002427602210230

DO - 10.5220/0002427602210230

M3 - Conference contribution

SN - 978-972-8865-93-1

SP - 221

EP - 230

BT - Proceedings of the 7th International Workshop on Pattern Recognition in Information Systems

A2 - Fred, A.

A2 - Jain, A.K.

PB - INSTICC PRESS

ER -

Boom B, Spreeuwers L, Veldhuis R. Automatic face alignment by maximizing similarity score. In Fred A, Jain AK, editors, Proceedings of the 7th International Workshop on Pattern Recognition in Information Systems. INSTICC PRESS. 2007. p. 221-230 https://doi.org/10.5220/0002427602210230