This project team would work on one or more parts of the following project.
We propose a project to conduct research into hybridizing the techniques of pattern recognition in order to develop a high-confidence user verification system. A user verification system can be embedded into any system that requires high security and can be developed in a variety of different modalities, and we propose four: face, fingerprint, handwriting, and voice input devices. Each of the four verification systems involves comparison of signal samples from the input device with those from the database and has type I (valid user rejected) and type II (invalid user accepted) errors. Hybridizing these four different verification techniques should achieve a high level of confidence.