Please use this identifier to cite or link to this item:
Title: Multi-spectral information regarding face recognition
Authors: Ticay-Rivas, Jaime R.
Del Pozo-Baños, Marcos
Travieso, Carlos M. 
Alonso, Jesús B. 
Ferrer, Miguel A. 
UNESCO Clasification: 3307 Tecnología electrónica
Keywords: Principal component analysis , Face , Feature extraction , Discrete cosine transforms , Discrete wavelet transforms , Databases , Support vector machines , Hyper-spectral Face Image , Face Verification , Pattern Recognition
Issue Date: 2011
Publisher: 1071-6572
Journal: Proceedings - International Carnahan Conference on Security Technology 
Conference: 2011 IEEE International Carnahan Conference on Security Technology, ICCST 2011 
Abstract: Recently, hyper-spectral facial image capturing techniques have opened a new door for creating innovative techniques aiming to improve these systems features. In our work, we have developed a verification approach based on Principal Component Analysis, and doing channel fusion (data fusion), in particular 5, 13, 14, 16, 24, 33, and 34 channels, reaching an Equal Error Rate of 97.37%; showing a good behavior of the kind of images.
ISBN: 9781457709029
ISSN: 1071-6572
DOI: 10.1109/CCST.2011.6095933
Source: Proceedings - International Carnahan Conference on Security Technology[ISSN 1071-6572] (06095933)
Appears in Collections:Actas de congresos
Show full item record

Page view(s)

checked on Feb 3, 2024

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.