A Novel Approach Based on Fingerprint Identification and Face Recognition
Main Article Content
Abstract
In real world applications unimodal biometrics have some limitations such as noise sensitivity, data quality, non-universality,
interclass difference. These issues can be tackled easily by multimodal biometric system. This paper investigates the fusion of face visual
features by using e-PCA that resolves the issue of visual difference in face classification process. An implementation of face and fingerprint
fusion using PCA based and hamming distance for calculating minutiae features in fingerprint is fused at matching score level .This paper uses
match score level by choosing the id of both face and fingerprint Better result can be obtained using Euler PCA if multiple instances of same
person were used for matching and combining. Templates of fingerprint and face feature are tested on self created image database. PCA
observes different dimensions and evaluate the principle dimensions where the variation is high. This proposed work is tested in MATLAB
2015b with performance metrics FAR of 3.33%, FRR of 3.27 and accuracy by changing the person instance feature at every time.
Â
Keywords: Biometrics, ePCA, PCA, Biometrics Technique, Multimodal Biometric
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.