Paper Info
Title
Biometric verification/identification based on hands natural layout
Abstract
In this paper, a hand biometric system for verification and recognition purposes is presented. The method is based on three keys. Firstly, the system is based on using a Natural Reference System (NRS) defined on the hand's natural layout. Consequently, neither hand-pose training nor a pre-fixed position is required in the registration process. Secondly, the hand's features are obtained through the polar representation of the hand's contour. This implies minimum image processing and low computational cost. Thirdly, instead of common methods that use one hand, we use right and left hands. This allows us to consider distance measures for direct (R/R,L/L) and crossed (R/L,L/R) hands obtaining improvements in FAR/FRR and identification ratios. The paper shows details about the experimentation and presents the results of the method applied on 5640 images belonging to 470 users. The results are good enough to consider this biometric system for future security/control applications.
Year
DOI
Venue
2008
10.1016/j.imavis.2007.08.010
Image Vision Comput.
Keywords
Field
DocType
control application,natural reference system,hands natural layout,left hand,hand-pose training,distance measure,hand biometric system,identification ratio,future security,biometric system,biometric verification,common method,security,hand geometry,similarity,system security
Computer vision,Hand geometry,Pattern recognition,Computer science,Image processing,Artificial intelligence,Biometrics,Biometric system,Distance measures
Journal
Volume
Issue
ISSN
26
4
Image and Vision Computing
Citations 
PageRank 
References 
16
0.77
15
Authors
4
Name
Order
Citations
PageRank
Miguel Adán1536.16
Antonio Adán212422.27
Andrés S. Vázquez38210.75
Roberto Torres415914.30