Biometric verification/identification based on hands natural layout

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. (C) 2007 Elsevier B.V. All rights reserved.