Design of a vision system for identity verification

The use of biometric data for automated identity verification, is one of the major challenges in many application domains. This is certainly a formidable task which requires the development of a complex system including several concurrent agents operating in real time. In this paper a system for automated identity verification (currently under development within an European research project) encompassing the active vision paradigm is described. In our approach the amount of data to be processed is limited by selecting and analysing only few areas within the face image. The number of pixels for each area are also reduced by applying a space-variant conformal mapping. The devised system does not require to use special hardware. On the other hand, robustness can be enforced by performing the final matching with more than a single image. This may require to adopt a simple, coarse scale, multi-processor architecture. The system is conceived for banking applications but can be ported to a variety of industrial applications. Several experiment's on identity verification, performed on real images, are presented.