Decision fusion for hand biometric authentication

In this paper, we present a multibiometric approach which combines palmprint, fingerprint and finger geometry collected by a digital camera at decision fusion level. First, eight neighborhood border tracing algorithm is applied to locate fingertips and valley points, then the regions of palmprint and fingerprint as well as a finger contour are extracted from a whole-hand image. Second, the linear discriminant analysis is used to extract palmprint and fingerprint features, and finger geometry feature is obtained from the finger contour. Finally, three decision fusion rules, including ¿AND¿ rule, ¿OR¿ rule and majority voting, are employed to perform the fusion. Experimental results conducted on a database of 86 hands (10 impressions per hand) show that the proposed decision fusion methods are effective.