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 prealignment 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 preprocessing step in a Fuzzy Vault scheme. |
Year | Venue | Keywords |
---|---|---|
2019 | 2019 International Conference of the Biometrics Special Interest Group (BIOSIG) | Fingerprint Registration,Deep Learning,Fingerprint Pre-Alignment,Biometric Template Protection |
Field | DocType | ISBN |
Vertical translation,Computer vision,Pattern recognition,Fingerprint recognition,Computer science,Fingerprint,Robustness (computer science),Preprocessor,Artificial intelligence,Deep learning,Cross-validation,Computation | Conference | 978-1-7281-2677-7 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Benjamin Dieckmann | 1 | 0 | 0.68 |
Johannes Merkle | 2 | 75 | 12.14 |
Christian Rathgeb | 3 | 551 | 55.72 |