Abstract
Multimodal biometric systems which fuse information from a number of biometrics, are gaining more attentions lately because they are able to overcome limitations in unimodal biometric systems. These systems are suited for high security applications. Most of the proposed multibiometric systems offer one level of security. In this paper a new approach for adaptive combination of multiple biometrics has been proposed to ensure multiple levels of security. The score level fusion rule is adapted using (PSO) Particle Swarm Optimization to ensure the desired system performance corresponding to the desired level of security. The experimental results prove that the proposed multimodal biometric system is appropriate for applications that require different levels of security.
Highlights
The biometric technologies cover a wide range of applications that can be used to verify person identity by measuring human physiological or behavioral characteristics
The performance of the biometric identification system is measured by False Acceptance Rate (FAR) and False Rejection Rate (FRR) or Genuine Acceptance Rate (GAR)
FRR, False Acceptance Rrate (FAR), GAR and Total Error Rate (TER) are determined as follow: FAR(%) false accep tan ce numbers X100%
Summary
The biometric technologies cover a wide range of applications that can be used to verify person identity by measuring human physiological or behavioral characteristics. Unimodal biometric systems perform person recognition based on a single source of biometric information. Such systems are often affected by some problems such as noisy sensor data and nonuniversality, inter-class similarities, and spoof attacks. Due to these practical problems, the error rates associated with unimodal biometric systems are quite high and it makes them unacceptable for deployment in security critical applications [1]. Some of the problems that affect unimodal biometric systems can be avoided by using multimodal biometric systems Morever multibiometric systems may be viewed as fault tolerant systems
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have