IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans - Special issue on recent advances in biometrics
K-means based fingerprint segmentation with sensor interoperability
EURASIP Journal on Advances in Signal Processing
GUC100 multisensor fingerprint database for in-house (semipublic) performance test
EURASIP Journal on Information Security
| Hi-index | 0.00 |
Biometric sensor interoperability refers to the ability of a system to compensate for the variability introduced in the biometric data of an individual due to the deployment of different sensors. Poor inter-sensor performance has been reported in different biometric domains including fingerprint, face, iris and speech. In the context of fingerprints, variations are observed in the acquired images due to differences in sensor resolution, scanning area, sensing technology, etc. which impact the feature set extracted from these images. The inability of a fingerprint matcher to compensate for these variations introduced in fingerprints acquired using different sensors results in inferior inter-sensor performance. In this work it is demonstrated that a simple non-linear calibration scheme, based on Thin Plate Splines (TPS), is sufficient to facilitate sensor interoperability in the context of fingerprints. In the proposed technique, the variation between the images acquired using two different sensors is modeled using non-linear distortions. The proposed calibration model is tested on the MSU dataset comprising of fingerprint images obtained using two different sensor technologies: an optical Digital Biometrics (DBI) sensor and a solid-state capacitive VERIDICOM (VERI) sensor. Experiments indicate that the proposed calibration scheme improves the inter-sensor Genuine Accept Rate (GAR) by ~35% to ~40% at a False Accept Rate (FAR) of 0.01%.