Fingerprint Pre-Alignment based on Deep Learning

Abstract

Robust fingerprint pre-alignment is vital for identification systems and biometric cryptosystems based on fingerprint minutiae, where computation of a relative alignment by comparison of the fingerprints is inefficient or intractable, respectively. The pre-alignment is achieved through an absolute alignment, i. e. an alignment computed for each fingerprint independently, which can be applied for fingerprint registration to compensate for variations in the placement (translation) and rotation of the fingerprints prior to their comparison. In this work, a deep learning approach for absolute pre-alignment of fingerprints is presented. The proposed algorithm employs a siamese network (with CNNs as subnetworks) which is trained on synthetically generated fingerprints using horizontal/vertical translation and rotation as three regression coefficients. Evaluations are conducted on the FVC2000 DB2a and the MCYT fingerprint database. Compared to other published fingerprint pre-alignment methods, the presented scheme achieves higher accuracy w. r. t. rotation estimation and overall robustness. In addition, the proposed pre-alignment is applied as a pre-processing step in a Fuzzy Vault scheme.