Abstract
The Journal of Surveillance, Security and Safety is an international, peer-reviewed, open access journal which provides a forum for the publication of papers addressing the variety of theoretical, methodological, epistemological, empirical and practical issues concerns reflected in the field of information security, cyber security, machine learning, emerging technologies, and their applications.
Highlights
As the utilization of digital devices and applications continues to grow, the need for more complex solutions to authenticate legitimate users is becoming essential
The proposed method achieved an False live rejection (FLR) of 0% and an False spoof acceptance (FSA) of 0% at threshold levels of 44.55, 40.75 and 31.6 for an optical scanner, a capacitive DC scanner and an opto-electrical scanner, respectively
average classification error (ACE) of 2.9% ACC of 97.10% CaffeNet (96.5%) GoogLeNet (96.6%) Siamese (93.1%) ACE 1.75% attack presentation classification error rate (APCER) < 7.3% and an bona fide presentation classification error rate (BPCER) = 1% Average accuracy 95.3% Not good generalization to unknown Presentation attack instrument (PAI) ACE of 1.35%
Summary
As the utilization of digital devices and applications continues to grow, the need for more complex solutions to authenticate legitimate users is becoming essential. In this context, biometric-based authentication systems are being increasingly employed as they can be found almost everywhere, including in smartphones, laptops and so on. Fingerprint recognition is based on the Galton points [Figure 1], named after Sir Francis Galton, who in the late nineteenth century used the so-called Galton points to categorize the attributes of a finger that are utilized to identify a person. These systems use more than one finger to produce the biometric identity of a user
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.