Skip to main content

Visual intelligent recognition for secure banking services


The goal of this Reactive LTR project is to realise a prototype autonomous station for personal identification. This station will include all the features required to be integrated into a new generation of automated security check-point along corridors, passageways or access doors, and in the next-generation of automatic teller machines. This prototype will be used to perform a significant set of statistical tests on personal identification.

Secure access control is a key issue in banking services. Magnetic cards and personal identification numbers, currently adopted for accessing automatic tellers, do not provide a sufficient degree of security and are likely a source for unauthorised operations. As far as the access to restricted areas is concerned, it usually requires direct surveillance by guards or indirect surveillance by a human operator through a monitoring system. Even in this case it is often difficult, due to fatigue or other distracting factors, to guarantee continuous and high performance in this task.

The project is mainly focused on banking services, in particular for secure and safe control of access to key areas in the bank building and for cross-checking personal identity of people requesting banking transactions. A system based on visual recognition will have a major impact on man machine interaction, providing a more natural way for the customer to interact with the banking security system. The project will also have a potential impact in various scenarios ranging from generic surveillance in buildings and parking areas to security control through check points in airports or railway stations.

As such, it represents up-stream RTD feeding RTD Task 1.24: Human Comfort and Security which aims to accelerate the development of new or existing user interface components, technologies, and techniques which will improve individual interaction thus increasing efficiency, flexibility, safety and acceptance. The industrial sponsors are committed to the completion of the down-stream RTD work and to its subsequent commercial exploitation.

Our approach will be to exploit newly-developed advanced techniques based on computer vision and robotics. Iconic and feature-based techniques will be utilised in the first instance and in case of ambiguities, performances will be improved by using stereo analysis and the general theory of projective invariants. A breakthrough with respect to current technology will be given by the use of space-variant image representation and by the realisation of an active robotic system, able to fixate and track the examined subject.

Funding Scheme

CSC - Cost-sharing contracts


Dipartimento diInformatica Sistemistica E Telematica - Universita Degli Studi diGenova
Via Opera Pia 13
16145 Genova

Participants (4)

Ecole Polytechnique Federale Lausanne
Signal Processing Laboratory
1015 Lausanne
1,Av. Rovisco Pais
1096 Lisboa Codex
Via De'cattani 220G
50145 Firenze
National University Ireland, Maynooth