Recurrent Binary Patterns and CNNs for Offline Signature Verification


YILMAZ M. B., Ozturk K.

Future Technologies Conference (FTC), San-Francisco, Costa Rica, 24 - 25 October 2019, vol.1070, pp.417-434 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 1070
  • Doi Number: 10.1007/978-3-030-32523-7_29
  • City: San-Francisco
  • Country: Costa Rica
  • Page Numbers: pp.417-434
  • Keywords: Offline signature verification, Recurrent neural network, Convolutional neural network, Score-level integration, NEURAL-NETWORKS
  • Akdeniz University Affiliated: Yes

Abstract

Signature representations that are extracted by convolutional neural networks (CNN) can achieve low error rates. However, a trade-off exists between such models' complexities and hand-crafted features' slightly higher error rates. A novel writer-dependent (WD) recurrent binary pattern (RBP) network, and a novel signer identification CNN is proposed. RBP network is a recurrent neural network (RNN) to learn the sequential relation between binary pattern histograms over image windows. A novel histogram selection method is introduced to remove the stop-word codes. Dimensionality is reduced by more than 25% while improving the results. This work is the first to combine binary patterns and RNNs for static signature verification. Several test sets, derived from large-scale and popular databases (GPDS-960 and GPDS-Synthetic-10000) are used. Without training any global classifier, RBP network provides competitive equal error rates (EER). The proposed architectures are compared and integrated with other recent CNN models. Score-level integration of WD classifiers trained with different representations are investigated. Cross-validation tests demonstrate the EERs reduced compared to the best single classifier. A state-of-the-art EER of 1.11% is reported with a global decision threshold (0.57% EER with user-based thresholds) on GPDS-160 database.