In recent years the cost and size of biometric sensors and processing engines has fallen, a growing trend towards e-commerce, teleworking and e-banking has emerged and people's attitude to security since September 11th has shifted. For these reasons there has been a rapid increase in the use of biometric technology in a range of different applications. For example, at Schipol Airport in Amsterdam, frequent flyers are able to use their iris scans to check-in for flights. The same technology is also used to grant access to airport personnel in secure areas. In Spain, fingerprint scans are used on social security cards and in the U.S.A the Federal Bureau of Prisons uses hand geometry to track the movements of its prisoners, staff and visitors within its prisons.
However, even though these are all fairly reliable methods of biometric personal authentication they are unacceptable by users in all but these high-security situations. They require both user co-operation and are considered intrusive. In contrast, personal identification systems based on the analysis of speech and face images are non-intrusive and more user-friendly. Moreover, personal identity can be often ascertained without the client's assistance. However, speech and image-based systems are more susceptible to imposter attack, especially if the imposter possesses information about a client, eg. a photograph or a recording of client's speech. Multi-modal personal verification is one of the most promising approaches to user-friendly (hence acceptable) highly secure personal verification systems.
BANCA is a European project whose aim is to develop and implement a secure system with enhanced identification, authentication and access control schemes for applications over the Internet such as tele-working and Web - or remote - banking services. One of the major innovations targeted by this project is to obtain an enhanced security system by combining classical security protocols with robust multi-modal verification schemes based on speech and face images.
Any comments or general enquiries please contact: Chi Ho Chan (Chiho.Chan@surrey.ac.uk)