IEICE Technical Committee Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
Tech. Rep. Archives
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2012-08-28 13:30
Biometric Authentication System Based on Generalized Linear Mixed Model
Yosuke Kaga, Kenta Takahashi, Takao Murakami, Osamu Takata, Hisao Sakazaki (Hitachi, Ltd.)
Abstract (in Japanese) (See Japanese page) 
(in English) Some biometric authentication methods based on multiple biometric information are proposed.
In these conventional methods, multiple similarities are calculated by matching between multiple enrolled biometric information and user's biometric information.
By statistical processing of multiple similarities, the fusion decision whether the user is genuine or not is realized.
The statistical processing in the conventional methods is simple calculation such as sum rule, and each similarity is equally used in the statistical processing.
However, if the quality of biometric information differ from each other, the conventional methods cannot accurately decide whether the user is genuine or not.
To solve this problem, we proposed accurate fusion decision method based on generalized linear mixed model (GLMM).
However, in our method, GLMM based learning is required at every biometric information enrollment, and the computational complexity of the learning is very high.
In this paper, we propose fast fusion decision method based on the GLMM.
In our method, the fixed effects of GLMM are estimated previously, and the only mixed effects of GLMM are estimated at every biometric information enrollment.
The results of evaluation experiments based on fingerprint images are shown, and the effectiveness of our method is confirmed.
Keyword (in Japanese) (See Japanese page) 
(in English) biometrics / generalized linear mixed model / fusion decision / / / / /  
Reference Info. IEICE Tech. Rep.
Paper #  
Date of Issue  
ISSN  
Download PDF

Conference Information
Committee BioX  
Conference Date 2012-08-27 - 2012-08-28 
Place (in Japanese) (See Japanese page) 
Place (in English) Waseda Univ. Nishiwaseda Campus 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Biometrics, etc. 
Paper Information
Registration To BioX 
Conference Code 2012-08-BioX 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Biometric Authentication System Based on Generalized Linear Mixed Model 
Sub Title (in English)  
Keyword(1) biometrics  
Keyword(2) generalized linear mixed model  
Keyword(3) fusion decision  
Keyword(4)  
Keyword(5)  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Yosuke Kaga  
1st Author's Affiliation Yokohama Research Laboratory, Hitachi, Ltd. (Hitachi, Ltd.)
2nd Author's Name Kenta Takahashi  
2nd Author's Affiliation Yokohama Research Laboratory, Hitachi, Ltd. (Hitachi, Ltd.)
3rd Author's Name Takao Murakami  
3rd Author's Affiliation Yokohama Research Laboratory, Hitachi, Ltd. (Hitachi, Ltd.)
4th Author's Name Osamu Takata  
4th Author's Affiliation Yokohama Research Laboratory, Hitachi, Ltd. (Hitachi, Ltd.)
5th Author's Name Hisao Sakazaki  
5th Author's Affiliation Yokohama Research Laboratory, Hitachi, Ltd. (Hitachi, Ltd.)
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2012-08-28 13:30:00 
Presentation Time 30 minutes 
Registration for BioX 
Paper #  
Volume (vol) vol. 
Number (no)  
Page  
#Pages  
Date of Issue  


[Return to Top Page]

[Return to IEICE Web Page]


The Institute of Electronics, Information and Communication Engineers (IEICE), Japan