On design and optimization of face verification systems that are smart-card based

The optimization of a smart card face verification system is a very complex process with many key factors to consider. It involves the investigation of the effect the system parameters have on the system performance measured in terms of accuracy and speed. As the parameters involved are not independent, the search space is of exponential complexity. In practice only partial optimization is feasible with many parameters forced to take default values. We argue that the key options to optimize are image resolution or/and image pre-processing. 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 smart card. In this work we investigate different optimization strategies by considering both image compression and image resolution, and demonstrate that both the system performance and speed of access can be improved by the jointly optimized parameter setting and the level of probe compression. The experimental results obtained on the XM2VTS database suggest that the choice of one strategy over another is a matter of the time available for the system design, system performance, and response time.