SynSig2Vec: Learning Representations from Synthetic Dynamic Signatures for Real-World Verification

  • Songxuan Lai South China University of Technology
  • Lianwen Jin South China University of Technology
  • Luojun Lin South China University of Technology
  • Yecheng Zhu South China University of Technology
  • Huiyun Mao South China University of Technology

Abstract

An open research problem in automatic signature verification is the skilled forgery attacks. However, the skilled forgeries are very difficult to acquire for representation learning. To tackle this issue, this paper proposes to learn dynamic signature representations through ranking synthesized signatures. First, a neuromotor inspired signature synthesis method is proposed to synthesize signatures with different distortion levels for any template signature. Then, given the templates, we construct a lightweight one-dimensional convolutional network to learn to rank the synthesized samples, and directly optimize the average precision of the ranking to exploit relative and fine-grained signature similarities. Finally, after training, fixed-length representations can be extracted from dynamic signatures of variable lengths for verification. One highlight of our method is that it requires neither skilled nor random forgeries for training, yet it surpasses the state-of-the-art by a large margin on two public benchmarks.

Published
2020-04-03
Section
AAAI Technical Track: Applications