Matcher fusion is a recognized approach for improving biometric system performance. Our interest in fusion was largely to determine how much performance headroom exists with current matcher technology. We employed five latent fingerprint matchers, having the ability to use alternate input data (features); this allows the influence of data type to be investigated. Numerical results show it is possible to reduce the final candidate list to two to six candidates, with the probability that the true mate appears in the top (first) position boosted by 6 15%-points.
Conference Dates: March 29-April 1, 2012
Conference Location: New Delhi, -1
Conference Title: 5th IAPR International Conference on Biometrics
Pub Type: Conferences
latent fingerprint matching, automated matching, matcher fusion, biometrics