Offline signature verification using a region based deep metric learning network. (October 2021)

• Record Type: Journal Article
• Authors: Liu, Li; Huang, Linlin; Yin, Fei; Chen, Youbin
• Is Part Of: Pattern recognition. Volume 118(2021)
• Publication Date: 2021-10
• Subjects: Signature verification -- Convolutional siamese network -- Deep metric learning -- Region fusion; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108009
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A region based deep convolutional Siamese network is proposed for feature and metric learning in offline signature verification A Mutual Signature DenseNet (MSDN) is designed to extract discriminative features by interaction between two input signatures. Superior performance of both writer-independent and writer-dependent signature verification are reported on public datasets. Abstract: Handwritten signature verification is a widely used biometric for person identity authentication in document forensics. Despite the tremendous efforts in past research, offline signature verification still remains a challenge, particularly in discriminating between genuine signatures and skilled forgeries, because the difference of appearance between genuine and skilled forgery may be smaller than that between genuine ones. This challenge is even more critical in writer-independent scenario, where each writer has very few samples for training. This paper proposes a region based Deep Convolutional Siamese Network using metric learning method, which is applicable to both writer-dependent (WD) and writer-independent (WI) scenario. For representing minute but discriminative details, a Mutual Signature DenseNet (MSDN) is designed to extract features and learn the similarity measure from local regions instead of whole signature images. Based on local regions comparison, the similarity scores of multiple regions are fused for final decision of verification. In experiments on public datasets CEDAR and GPDS, the proposed method achieved state-of-the-art performance of 6.74% EER and 8.24% EER in WI scenario, respectively, and 1.67% EER and 1.65% EER in WD scenario, respectively.