An efficient face identification method in a transformed domain

Marcos Faundez-Zanuy; Virginia Espinosa-Duró; Juan Antonio Ortega

doi:10.1109/CCST.2007.4373501

An efficient face identification method in a transformed domain

Marcos Faundez-Zanuy^*
, Virginia Espinosa-Duró
, Juan Antonio Ortega

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

In this paper we propose a low-complexity face recognition system based on the Walsh-Hadamard transform. This system can be easily implemented on a fixed point processor and offers a good compromise between computational burden and identification rates. We have evaluated that with 169 integer coefficients per face we achieve better results (92%) than the classical eigenfaces approach (86.5%), and close to the DCT (92.5%) with a reduced computational cost.

Original language	English
Title of host publication	Proceedings 2007 41st Annual IEEE International Carnahan Conference on Security Technology, ICCST
Pages	281-284
Number of pages	4
DOIs	https://doi.org/10.1109/CCST.2007.4373501
Publication status	Published - 2007
Externally published	Yes
Event	2007 41st Annual IEEE Carnahan Conference on Security Technology, ICCST - Ottawa, ON, Canada Duration: 8 Oct 2008 → 11 Oct 2008

Publication series

Name	Proceedings - International Carnahan Conference on Security Technology
ISSN (Print)	1071-6572

Conference

Conference	2007 41st Annual IEEE Carnahan Conference on Security Technology, ICCST
Country/Territory	Canada
City	Ottawa, ON
Period	8/10/08 → 11/10/08

Keywords

Biometrics
Face recognition
Fast algorithms
Walsh Hadamard Transfrom (WHT)

Access to Document

10.1109/CCST.2007.4373501

Cite this

Faundez-Zanuy, M., Espinosa-Duró, V., & Ortega, J. A. (2007). An efficient face identification method in a transformed domain. In Proceedings 2007 41st Annual IEEE International Carnahan Conference on Security Technology, ICCST (pp. 281-284). Article 4373501 (Proceedings - International Carnahan Conference on Security Technology). https://doi.org/10.1109/CCST.2007.4373501

@inproceedings{edf2fba84988436aa8f5914d94432f3d,

title = "An efficient face identification method in a transformed domain",

abstract = "In this paper we propose a low-complexity face recognition system based on the Walsh-Hadamard transform. This system can be easily implemented on a fixed point processor and offers a good compromise between computational burden and identification rates. We have evaluated that with 169 integer coefficients per face we achieve better results (92\%) than the classical eigenfaces approach (86.5\%), and close to the DCT (92.5\%) with a reduced computational cost.",

keywords = "Biometrics, Face recognition, Fast algorithms, Walsh Hadamard Transfrom (WHT)",

author = "Marcos Faundez-Zanuy and Virginia Espinosa-Dur{\'o} and Ortega, \{Juan Antonio\}",

year = "2007",

doi = "10.1109/CCST.2007.4373501",

language = "English",

isbn = "1424411297",

series = "Proceedings - International Carnahan Conference on Security Technology",

pages = "281--284",

booktitle = "Proceedings 2007 41st Annual IEEE International Carnahan Conference on Security Technology, ICCST",

note = "2007 41st Annual IEEE Carnahan Conference on Security Technology, ICCST ; Conference date: 08-10-2008 Through 11-10-2008",

}

Faundez-Zanuy, M, Espinosa-Duró, V & Ortega, JA 2007, An efficient face identification method in a transformed domain. in Proceedings 2007 41st Annual IEEE International Carnahan Conference on Security Technology, ICCST., 4373501, Proceedings - International Carnahan Conference on Security Technology, pp. 281-284, 2007 41st Annual IEEE Carnahan Conference on Security Technology, ICCST, Ottawa, ON, Canada, 8/10/08. https://doi.org/10.1109/CCST.2007.4373501

An efficient face identification method in a transformed domain. / Faundez-Zanuy, Marcos; Espinosa-Duró, Virginia; Ortega, Juan Antonio.
Proceedings 2007 41st Annual IEEE International Carnahan Conference on Security Technology, ICCST. 2007. p. 281-284 4373501 (Proceedings - International Carnahan Conference on Security Technology).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An efficient face identification method in a transformed domain

AU - Faundez-Zanuy, Marcos

AU - Espinosa-Duró, Virginia

AU - Ortega, Juan Antonio

PY - 2007

Y1 - 2007

N2 - In this paper we propose a low-complexity face recognition system based on the Walsh-Hadamard transform. This system can be easily implemented on a fixed point processor and offers a good compromise between computational burden and identification rates. We have evaluated that with 169 integer coefficients per face we achieve better results (92%) than the classical eigenfaces approach (86.5%), and close to the DCT (92.5%) with a reduced computational cost.

AB - In this paper we propose a low-complexity face recognition system based on the Walsh-Hadamard transform. This system can be easily implemented on a fixed point processor and offers a good compromise between computational burden and identification rates. We have evaluated that with 169 integer coefficients per face we achieve better results (92%) than the classical eigenfaces approach (86.5%), and close to the DCT (92.5%) with a reduced computational cost.

KW - Biometrics

KW - Face recognition

KW - Fast algorithms

KW - Walsh Hadamard Transfrom (WHT)

UR - https://www.scopus.com/pages/publications/47849119736

U2 - 10.1109/CCST.2007.4373501

DO - 10.1109/CCST.2007.4373501

M3 - Conference contribution

AN - SCOPUS:47849119736

SN - 1424411297

SN - 9781424411290

T3 - Proceedings - International Carnahan Conference on Security Technology

SP - 281

EP - 284

BT - Proceedings 2007 41st Annual IEEE International Carnahan Conference on Security Technology, ICCST

T2 - 2007 41st Annual IEEE Carnahan Conference on Security Technology, ICCST

Y2 - 8 October 2008 through 11 October 2008

ER -

An efficient face identification method in a transformed domain

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this