Compensating for variable recording conditions in frontal face authentication algorithms

A. Tefas; Y. Menguy; C. Kotropoulos; G. Richard; I. Pitas; P. Lockwood

doi:10.1109/icassp.1999.757612

Compensating for variable recording conditions in frontal face authentication algorithms

A. Tefas
, Y. Menguy
, C. Kotropoulos
, G. Richard
, I. Pitas
, P. Lockwood

Aristotle University of Thessaloniki

Résultats de recherche: Contribution à un journal › Article de conférence › Revue par des pairs

1 Citation (Scopus)

Résumé

This paper addresses the problem of compensating for variable recording conditions such as changes in illumination, scale differences, varying face position. It is well known that the performance of any face authentication/ recognition algorithm deteriorates significantly in the presence of the aforementioned conditions as well as the expression variations. The use of simple and powerful pre-processing techniques aiming at compensating for variable recording conditions prior to the application of any authentication algorithm is proposed. It is shown that such an approach overcomes indeed the image variations and guarantees an almost stable performance for the Morphological Dynamic Link Architecture developed within the European research project M2VTS.

langue originale	Anglais
Pages (de - à)	3561-3564
Nombre de pages	4
journal	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	6
Les DOIs	https://doi.org/10.1109/icassp.1999.757612
état	Publié - 1 janv. 1999
Modification externe	Oui
Evénement	Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99) - Phoenix, AZ, USA Durée: 15 mars 1999 → 19 mars 1999

Accès au document

10.1109/icassp.1999.757612

Contient cette citation

@article{af6385767a7847aa84c19d49df51d8bc,

title = "Compensating for variable recording conditions in frontal face authentication algorithms",

abstract = "This paper addresses the problem of compensating for variable recording conditions such as changes in illumination, scale differences, varying face position. It is well known that the performance of any face authentication/ recognition algorithm deteriorates significantly in the presence of the aforementioned conditions as well as the expression variations. The use of simple and powerful pre-processing techniques aiming at compensating for variable recording conditions prior to the application of any authentication algorithm is proposed. It is shown that such an approach overcomes indeed the image variations and guarantees an almost stable performance for the Morphological Dynamic Link Architecture developed within the European research project M2VTS.",

author = "A. Tefas and Y. Menguy and C. Kotropoulos and G. Richard and I. Pitas and P. Lockwood",

year = "1999",

month = jan,

day = "1",

doi = "10.1109/icassp.1999.757612",

language = "English",

volume = "6",

pages = "3561--3564",

journal = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

issn = "1520-6149",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99) ; Conference date: 15-03-1999 Through 19-03-1999",

}

Compensating for variable recording conditions in frontal face authentication algorithms. / Tefas, A.; Menguy, Y.; Kotropoulos, C. et al.
Dans: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Vol 6, 01.01.1999, p. 3561-3564.

Résultats de recherche: Contribution à un journal › Article de conférence › Revue par des pairs

TY - JOUR

T1 - Compensating for variable recording conditions in frontal face authentication algorithms

AU - Tefas, A.

AU - Menguy, Y.

AU - Kotropoulos, C.

AU - Richard, G.

AU - Pitas, I.

AU - Lockwood, P.

PY - 1999/1/1

Y1 - 1999/1/1

N2 - This paper addresses the problem of compensating for variable recording conditions such as changes in illumination, scale differences, varying face position. It is well known that the performance of any face authentication/ recognition algorithm deteriorates significantly in the presence of the aforementioned conditions as well as the expression variations. The use of simple and powerful pre-processing techniques aiming at compensating for variable recording conditions prior to the application of any authentication algorithm is proposed. It is shown that such an approach overcomes indeed the image variations and guarantees an almost stable performance for the Morphological Dynamic Link Architecture developed within the European research project M2VTS.

AB - This paper addresses the problem of compensating for variable recording conditions such as changes in illumination, scale differences, varying face position. It is well known that the performance of any face authentication/ recognition algorithm deteriorates significantly in the presence of the aforementioned conditions as well as the expression variations. The use of simple and powerful pre-processing techniques aiming at compensating for variable recording conditions prior to the application of any authentication algorithm is proposed. It is shown that such an approach overcomes indeed the image variations and guarantees an almost stable performance for the Morphological Dynamic Link Architecture developed within the European research project M2VTS.

U2 - 10.1109/icassp.1999.757612

DO - 10.1109/icassp.1999.757612

M3 - Conference article

AN - SCOPUS:0032665492

SN - 1520-6149

VL - 6

SP - 3561

EP - 3564

JO - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

JF - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

T2 - Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99)

Y2 - 15 March 1999 through 19 March 1999

ER -

Compensating for variable recording conditions in frontal face authentication algorithms

Résumé

Accès au document

Empreinte digitale

Contient cette citation