Abstract
The paper presents a people identity verification system based on the matching of top view finger snapshots, supplementing purely geometrical finger shape comparison with textural information. Low dimensional feature vectors are used to train binary classifiers based on small Gaussian Basis Functions networks which, in this task, are able to match Support Vector Machines performance while outperforming them in runtime efficiency, thereby exposing a different facet in the comparison which complements available literature reports.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have