Date of Graduation
Statler College of Engineering and Mineral Resources
Lane Department of Computer Science and Electrical Engineering
Improvements in contactless fingerprinting have resulted in contactless fingerprints becoming a faster and more convenient alternative to contact fingerprints. The interoperability between contactless fingerprints and contact fingerprints and how demographic factors can change interoperability has been challenging since COVID-19; the need for hygienic alternatives has only grown because of the sudden focus during the pandemic. Past work has shown issues with the interoperability of contactless prints from kiosk devices and phone fingerprint collection apps. Demographic bias in photography for facial recognition could affect photographed fingerprints. The paper focuses on evaluating match performance between contact and contactless fingerprints and evaluating match score bias based on five skin demographics; melanin, erythema, and the three measurements of the CIELab color space. The interoperability of three fingerprint matchers was tested. The best and worst Area Under the Curve (AUC) and Equal Error Rate (EER) values for the best-performing matcher were an AUC of 0.99398 and 0.97873 and an EER of 0.03016 and 0.07555, respectively, while the best contactless AUC and EER were 0.99337 and 0.03387 indicating that contactless match performance can be as good as contact fingerprints depending on the device. In contrast, the best and worst AUC and EER for the cellphone contactless fingerprints were an AUC of 0.96812 and 0.85772 and an EER of 0.08699 and 0.22130, falling short of the lowest performing contact fingerprints. Demographic analysis was on the top two of the three matchers based on the top one percent of non-match scores. Resulting efforts found matcher-specific bias for melanin showing specific ranges affected by low and high melanin values. While higher levels of erythema and general redness of the skin improved performance. Higher lightness values showed a decreased performance in the top-performing matcher.
Berti, Aeddon David, "Investigating the Impact of Demographic Factors on Contactless Fingerprint Interoperability" (2023). Graduate Theses, Dissertations, and Problem Reports. 11852.