Institutions considering biometrie deployments in IT security and e-commerce environments must investigate a range of questions, including costs, compatibility, scalability, and user acceptance. However, there are essential performance-related questions which can only be answered by looking at comparative, independent testing of biometrie technologies: How susceptible are biometrics to “accepting” impostors and “rejecting” authorized users? What is the likelihood of false matching and false non-matching for different technologies and different solutions? What percentage of users will be able to enrol in a given biometrie solution? Analysis of IBG Comparative Biometrie Testing results from different biometrie technologies — including finger-scan, facial-scan, voice-scan, signature-scan, iris-scan, and keystroke-scan — suggests that understanding biometrie system performance requires analysis of more than false match rates and false non-match rates generally provided by biometrie vendors. Two generally overlooked performance metrics may, in many cases, be critical determinants of a system’s overall effectiveness: failure to enrol rates and false non-match rates over time. These two metrics can be combined into a single metric known as Ability to Verify (ATV), a performance measure with a direct impact on system costs, security, and convenience. Testing shows that many ATV rates can vary substantially from technology to technology, and from biometrie device to biometrie device.
Weitere Kapitel dieses Buchs durch Wischen aufrufen
- Ability to Verify: A Metric for System Performance in Real-World Comparative Biometric Testing
- Springer US
- Chapter 15
Neuer Inhalt/© ITandMEDIA, Best Practices für die Mitarbeiter-Partizipation in der Produktentwicklung/© astrosystem | stock.adobe.com