Please use this identifier to cite or link to this item:
http://hdl.handle.net/10553/44093
| Title: | Arbitrary illumination conditions for facial identification | Authors: | Travieso, Carlos M. Alonso, Jesús B. Ferrer, Miguel A. |
UNESCO Clasification: | 3307 Tecnología electrónica | Keywords: | Lighting , Image databases , Support vector machines , Support vector machine classification , Principal component analysis , Neural networks , Biometrics , Face recognition , Robustness , Face detection , Biometric identification , facial recognition , classification system , neural network (NN) , support vector machines (SVM) | Issue Date: | 2007 | Publisher: | 1071-6572 | Journal: | Proceedings - International Carnahan Conference on Security Technology | Conference: | 41st Annual IEEE International Carnahan Conference on Security Technology 2007 41st Annual IEEE Carnahan Conference on Security Technology, ICCST |
Abstract: | This paper presents a simple, robust and novel for errors detection in biometric system which is applied to the Olivetti Research Laboratory (ORL) Face and Yale Databases. We have used as parameterisation different transformed dominions by James L. Wyman, et al. (2002), and a support vector machine (SVM) by Anil K. Jain, et al. (2004) as classifier. This system has been adjusted with our experiments for obtaining an false identification rate (FIR) of 0%, with a success rate of 90.8% a rejected samples rate of 9.2%. | URI: | http://hdl.handle.net/10553/44093 | ISBN: | 978-1-4244-1129-0 1424411297 |
ISSN: | 1071-6572 | DOI: | 10.1109/CCST.2007.4373474 | Source: | Proceedings - International Carnahan Conference on Security Technology[ISSN 1071-6572] (4373474), p. 93-98 |
| Appears in Collections: | Actas de congresos |
SCOPUSTM
Citations
1
checked on Apr 21, 2024
WEB OF SCIENCETM
Citations
3
checked on Feb 25, 2024
Page view(s)
66
checked on Feb 3, 2024
Google ScholarTM
Check
Altmetric
Share
Export metadata
Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.