Skip to Main Content
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 intersensor performance has been reported in different biometric domains including fingerprint, face, iris, and speech. In the context of fingerprint technology, variations are observed in the acquired images of a fingerprint due to differences in sensor resolution, scanning area, sensing technology, etc., which subsequently impact the feature set extracted from these images. The inability of a fingerprint matcher to compensate for these variations introduced by different sensors results in inferior intersensor matching performance. In this work, a nonlinear calibration scheme based on the Thin- Plate Spline (TPS) model is used to register a pair of fingerprint sensors. The proposed calibration technique relies on the evidence of a few image pairs acquired using the two sensors to generate an average deformation model that defines the spatial relationship between the two sensors. This assists in the systematic perturbation of images/features pertaining to one sensor in order to make them compatible with images/features originating from the other sensor. Experimental results using multiple fingerprint data sets confirm the efficacy of the proposed method in addressing intersensor geometric variations.