The performance of a biometric system depends on the quality of interaction of the biometric subject and the system. Past research has shown that fingerprint image quality is improved when the subjects received feedback from the system. However, the availability of feedback from current fingerprint systems is very limited. Currently, no feedback exists regarding the subjects hand positioning and how to correct any undesirable positions. In a study by Guan, Theofanos, Choong, and Stanton, the researchers designed a rich, quality-driven interactive real-time algorithm for detecting hand positioning and analyzing fingerprint images. This paper investigates if subjects can perform fingerprint self-captures by following the real-time system feedback and if an overlay guide will help with hand positioning. Eighty subjects participated in a controlled experiment with usability measures on efficiency, effectiveness and satisfaction of the system. The findings show that the real-time feedback fingerprint system is a highly usable system. By following the real-time, on-screen textual instructions, participants quickly learned, and felt comfortable and confident to capture their own fingerprints without any assistance. The overlay was perceived as helpful with hand positioning and providing visual feedback of where users hands were in relation to the scanner area. Based on the results, future research should focus on finding the best format to present the system feedback and investigating if users would benefit from all instructions in graphical format.
Conference Dates: September 23-26, 2012
Conference Location: DC, DC
Conference Title: The IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS 2012)
Pub Type: Conferences
fingerpint self-captures, biometric usability, real-time feedback, biometric symbols