Sensor-fusion-based biometric identity verification
- Sandia National Labs., Albuquerque, NM (United States)
- New Mexico State Univ., Las Cruces, NM (United States). Electronic Vision Research Lab.
Future generation automated human biometric identification and verification will require multiple features/sensors together with internal and external information sources to achieve high performance, accuracy, and reliability in uncontrolled environments. The primary objective of the proposed research is to develop a theoretical and practical basis for identifying and verifying people using standoff biometric features that can be obtained with minimal inconvenience during the verification process. The basic problem involves selecting sensors and discovering features that provide sufficient information to reliably verify a person`s identity under the uncertainties caused by measurement errors and tactics of uncooperative subjects. A system was developed for discovering hand, face, ear, and voice features and fusing them to verify the identity of people. The system obtains its robustness and reliability by fusing many coarse and easily measured features into a near minimal probability of error decision algorithm.
- Research Organization:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- AC04-94AL85000
- OSTI ID:
- 573302
- Report Number(s):
- SAND-98-0507; ON: DE98002845; TRN: 98:009257
- Resource Relation:
- Other Information: PBD: Feb 1998
- Country of Publication:
- United States
- Language:
- English
Similar Records
A performance evaluation of biometric identification devices
Status of personnel identity verifiers