Abstract:
Smart cards have become a common application that can perform a variety of secure transactions and have a significant number of advantages. They are however not secure enough in identifying the person using the smart card. Biometric in smart cards retains the functionality of the smart card while providing an extra layer of security to it. This study uses face and fingerprint biometric because fingerprint and face complement each other well. Face overcomes the non-universality problem of fingerprints, while fingerprint recognition has much higher accuracy than face recognition.
The main design issue is how to optimize image resolution and image preprocessing. In addition, the main design issue is the degree of compression that can be applied to the probe image before it is transmitted to the smartcard. In this research, image preprocessing and enhancement algorithms were employed to obtain templates for fingerprint and facial images, the fusion of the templates were stored in smartcard for verification and FAR and FRR used to determine the characterized performance of the multi biometric system.
The integrated system operates in identification mode with an admissible response time. In addition, the decison fusion scheme enables performance improvement by integrating multiple cues with different confidence measures.
Experimental results demonstrates that the system performs very well, it meets the response time as well as the accuracy requirements.
