Authentication of Swipe Fingerprint Scanners
Baras, John, S.
Date: September 01 - September 01, 2017
Swipe fingerprint scanners (sensors) can be distinguished based on their scanner pattern—a sufficiently unique, persistent, and unalterable intrinsic characteristic even to scanners of the same technology, manufacturer, and model. We propose a method to extract the scanner pattern from a single image acquired by a widely-used capacitive swipe fingerprint scanner and compare it with a similarly extracted pattern from another image acquired by the same or by another scanner. The method is extremely simple and computationally efficient as it based on moving-average filtering, yet it is very accurate and achieves an equal error rate below 0.1% for 27 swipe fingerprint scanners of exactly the same model. We also show the receiver operating characteristic for different decision thresholds of two modes of the method. The method can enhance the security of a biometric system by detecting an attack on the scanner in which an image containing the fingerprint pattern of the legitimate user and acquired by the authentic fingerprint scanner has been replaced by another image that may still contain the fingerprint pattern of the legitimate user but has been acquired by another, unauthentic fingerprint scanner, i.e., for scanner authentication.