Improved face recognition by combining information from multiple cameras in Automatic Border Control system

Automatic Border Control (ABC) systems employ biometrics for the identity verification of the travelers. Among the various biometric modalities, the face biometric is predominately used by considering its many advantages including contactless capture, non-intrusive and user-friendly interaction. Since the inflow of passengers at the airport is growing with time, the ABC systems are expected to work with high throughput. One way of addressing this is by performing the on-the-fly face recognition with ABC systems. However, due to various factors, including the change in illumination conditions, it is often challenging to capture a good quality face sample to facilitate a speedy biometric recognition with the ABC systems. One possible way to address this is by employing multiple cameras to capture different views of the face and then combine these views in the face recognition system. In this paper, we propose a framework for combining the information from multiple cameras to improve the face recognition accuracy. To this extent, we investigate five different fusion schemes to present an empirical study on a prototype version of MorphoWay™ ABC system. Extensive experiments are carried out on a database of 61 subjects that are recorded using a prototype version of MorphoWay™ ABC system in three different lighting conditions. The experimental results indicate the improvement in face recognition performance by combing information from multiple cameras in the prototype version of MorphoWay™ ABC system.