Fast Minutia-based Palmprint Matching Using CNN and Generalized Hough Transform

Abstract

Due to the large number of minutiae in a palmprint, the match-
ing process between two palm images is time consuming. One
way to address this issue is aligning all palmprint images to a ref-
erence image. In this paper, using convolutional neural network
(CNN) and generalized Hough transform (GHT), we propose a new
method to find the corresponding rotation and displacement be-
tween any palmprint and the reference palm image. Furthermore,
the proposed method is capable of distinguishing between left and
right palmprint automatically which helps to speed up the match-
ing process. The proposed registration method followed by minutia-
cylinder code (MCC) matching algorithm has been evaluated on the
THUPALMLAB database, and the results show the superiority of our
algorithm over most of the state-of-the-art.