Belief trees and networks for biometric applications

This paper aims to introduce the novel approach to the design of a class of decision-making tools based on belief networks for biometric applications. The problem is formulated as mapping the belief networks into the homogeneous computing network, in order to meet the requirements of real-time computing, in particular, the biometric-based physical access control system. The feasible approach to this problem is the accelerating of software computing using hardware. Our experiments show that the straightforward utilization of the hardware tools may not satisfy real-time applications, since the belief networks may not be mapped directly into the hardware. We propose generating the belief network based on mapping of the belief trees into the linear networks with further fusion, so that the obtained structures can be mapped into homogeneous computing arrays.