The performance of biometric authentication deteriorates when the underlying assumptions are violated due to nonlinear, nonstationary, and heterogeneous noise.
Depending on the number of observations N o, the estimated model and test will decrease the performance of the authentication system.
In this section, we discuss the throughput performance of the authentication protocol by considering the outage capacity and BER of the direct communication (DC, communication without the use of relay) and source relay destination communication paths.
In the experiments, we measure the performance of proposed authentication system with variable θ.
Through analysis and simulations, we have shown that the performance of the proposed authentication protocol is superior to using public key-based authentication mechanisms, for the metrics node energy and processing delay.
Figure 16 Impact of alterations on overall performance of the used authentication system among the 4 face databases.
An important contributing factor in the performance of a face authentication system is the metric used for defining a matching score.
Figure 16 shows that all the introduced alterations have an impact on overall performance of the used authentication matching algorithm presented in Section 4. Therefore, we define in Table 5 the quality sets definition for the used matching algorithm.
However, even though SC3 is not the most efficient in terms of authentication performance or complexity, compared to SC1 and SC2, it is the most secure, a merit that may make it the first choice in real-world applications.
