Abstract
Abstract Nowadays, there has been an increase in security concerns regarding fingerprint biometrics. This problem arises due to technological advancements in bypassing and hacking methodologies. This has sparked the need for a more secure platform for identification. In this paper, we have used a deep Convolutional Neural Network as a pre-verification filter to filter out bad or malicious fingerprints. As deep learning allows the system to be more accurate at detecting and reducing false identification by training itself again and again with test samples, the proposed method improves the security and accuracy by multiple folds. The implementation of a novel secure fingerprint verification platform that takes the optical image of a fingerprint as input is explained in this paper. The given input is pre-verified using Google’s pre-trained inception model for deep learning applications, and then passed through a minutia-based algorithm for user authentication. Then, the results are compared with existing models.
Highlights
We, human beings, are recognised by our unique characteristics and traits
By using the pre-verification phase, the security of the system can be increased. – We have applied the technique of transfer learning in the pre-verification phase. – Google’s Inception-v3, which is a pre-trained deep Convolutional Neural Network (CNN) model, is used for training the pre-verification phase. – Verification of the fingerprints is done by using Gabor filter and K-nearest neighbour (KNN)-based methods
We have done a novel experiment on fingerprint verification where the first phase is pre-filtering of bad fingerprints and the second phase is fingerprint verification
Summary
Human beings, are recognised by our unique characteristics and traits. These traits can be behavioural or physiological in nature. Identification and validation of individuals were done by information-based systems, which make use of passwords or cards for authentication As these methods are unreliable and less secure, the stored information can be hacked or lost. There has been a need for more secure, complex, and unique identifiers for user authentication Biometric traits such as such as fingerprints, palm prints, face, iris, and retina are found to be very useful for the recognition of individuals. Many systems today use algorithms that match the records in the database with the input provided by the scanner for user authentication As these methods in specific applications are not modified and updated regularly at a pace that equals or exceeds the progress made by malicious individuals, it leaves biometric recognition at an increased risk and makes them susceptible to cyber attacks. We are focusing mainly on fingerprint biometrics and how we can further improve its security by using enhanced verification platforms
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
