But early adoption has been hindered by the high costs of early products, coupled with complex installation and integration with existing security systems. In addition, many biometric solutions are monomodal, meaning they analyze only one human trait. As a result, their application tends to be limited because they have low tolerance to variation. Should a user wear glasses one day instead of contact lenses, or develop a minor finger injury, recognition problems could arise.

To counteract those challenges, multimodal biometric solutions have been developed that recognize more than one trait, helping to ensure tolerance, high recognition accuracy and maximum access protection. For example, software that identifies face, voice and lip movement allows for a higher degree of tolerance to variation. If a user has a sore throat and the voice pattern cannot be recognized, the software falls back on the two visual traits for verification.

Ensuring that security is not compromised, certain multimodal solutions give the system administrator the option of weighing the importance of each identifiable trait, customizing to decide which trait, if any, should be given priority. A balance can be struck between increased tolerance for slight changes in personal traits, leading to a lower false-rejection rate, or requiring agreement of all traits, resulting in a lower false-acceptance rate.

The majority of multimodal solutions have been layered-that is, trait recognition is done sequentially. This process tends to be slow. A simultaneous multimodal technology has been developed that can identify several human traits at once for a quicker, less obtrusive process.

Multimodal biometrics also relieves the technology of its perceived obtrusiveness. Recognition can be as simple and natural as saying hello to a friend. For example, the simultaneous identification of face, voice and lip movement from a single video clip eliminates the need for physical contact, such as placing a hand onto a plate for hand geometry identification. And, the client need not make a huge investment in specialized biometric devices like an iris scanner. Instead, a standard Web camera and microphone can be sufficient.

This technology is poised to alter the biometrics landscape and increase its acceptance by increasing security, simplifying use and lowering costs.

Michael Ruehle is Senior Vice President of Marketing at Bioid America (Raleigh, N.C.), the U.S. subsidiary of DCS AG (Berlin).