Feature generation and machine learning for robust multimodal biometrics
Abstract
Multimodal biometric systems are those that utilize more than one physiological or behavioral characteristic for verification or identification. In applications such as access and visitor control, airport (suspect identification, jetway surveillance, check in), face surveillance, attendance logging, DVR integration, hooligan control, robotics and network security, multimodal biometric systems are able to (i) reduce false non-match and false match rates, (2) provide a secondary means of verification, enrolment, and identification if sufficient data cannot be acquired from a given biometric sample, and (3) combat attempts to spoof biometric systems through non-live data sources such as fake fingers. Although biometric systems have made great strides, especially over recent years, there is continued need for vigorous research to solve many challenging problems still outstanding.
- Publication:
-
Pattern Recognition
- Pub Date:
- 2008
- DOI:
- 10.1016/j.patcog.2007.07.014
- Bibcode:
- 2008PatRe..41..775B