a_Thesis_AnalysisOfFingerprintRecognitionPerformanceOnInfants_SamuelReiff.pdf (2.42 MB)

Analysis of Fingerprint Recognition Performance on Infants

Download (2.42 MB)
thesis
posted on 29.07.2020 by Samuel J Reiff

In this study, any change in fingerprint performance, image quality and minutiae count for infants in three different age groups was evaluated (0-6, 7-12, and >12 months). This was done to determine whether there is a difference in performance between infant age groups for a fingerprint recognition system.

The purpose of this research was to determine whether there is a difference in infant fingerprint performance and image quality metrics, between three different age groups (0-6, 7-12, and >12 months old), using the same optical sensor? The data used for this secondary analysis was collected as part of a longitudinal multimodal infant study, using the Digital Persona U.are.U 4500. DET curves, zoo analysis, and image quality metrics were used to evaluate performance and quality factored by infant age group.

This study found that there was a difference in image quality and minutiae count, genuine and impostor match scores, and performance error rates (EER) between the three age groups. Therefore, quality and performance were dependent on age. While there was a difference in performance between age groups, there was generally stability for subjects who overlapped between multiple age groups. Difference in performance was most likely due to the difference in physical characteristics between subjects in each age group, rather than individual instability. The results showed that it could potentially be feasible to use fingerprint recognition for children over the age of 12 months.

History

Degree Type

Master of Science

Department

Technology Leadership and Innovation

Campus location

West Lafayette

Advisor/Supervisor/Committee Chair

Stephen Elliott

Additional Committee Member 2

Kevin O'Connor

Additional Committee Member 3

J. Eric Dietz

Licence

Exports