DocumentCode :
3200303
Title :
Biometrics security and experiments on face recognition algorithms
Author :
Dandashi, Amal ; Karam, Walid
Author_Institution :
Dept. of Comput. Sci., Univ. of Balamand, Koura, Lebanon
fYear :
2012
fDate :
11-13 July 2012
Firstpage :
1
Lastpage :
8
Abstract :
Biometrics security analysis and performance evaluation of the following Face Recognition Algorithms is performed: Principal Components Analysis (PCA), Linear Discriminant Analysis (LDA) and Bayesian Intrapersonal/Extrapersonal Classifier (BIC), using the BANCA database. Software tools retrieve and preprocess images from sequential records within the BANCA database for algorithm evaluation. Then a verification environment over the set of images to be tested is developed, the above algorithms are invoked over the verification set, and verification parameters are collected. Results proved PCA performed most accurately and effectively with regards to security concerns, with an average recognition rate of 93%, while LDA and BIC lagged behind with recognition rates ranging from 80%-83%.
Keywords :
Bayes methods; biometrics (access control); face recognition; image classification; principal component analysis; security of data; software tools; BANCA database; BIC; Bayesian intrapersonal/extrapersonal classifier; LDA; PCA; biometrics security analysis; face recognition algorithm; linear discriminant analysis; performance evaluation; principal components analysis; software tool; verification environment; verification parameter; verification set; Algorithm design and analysis; Biometrics; Databases; Face recognition; Principal component analysis; Testing; Training; BANCA Database; algorithms; biometrics security; face recognition; performance evaluation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence for Security and Defence Applications (CISDA), 2012 IEEE Symposium on
Conference_Location :
Ottawa, ON
Print_ISBN :
978-1-4673-1416-9
Type :
conf
DOI :
10.1109/CISDA.2012.6291532
Filename :
6291532
Link To Document :
بازگشت