Signature Verification Using a "Siamese" Time Delay Neural Network

Abstract

This paper describes an algorithm for verification of signatures written on a pen-input tablet. The algorithm is based on a novel, artificial neural network, called a "Siamese" neural network. This network consists of two identical sub-networks joined at their out(cid:173) puts. During training the two sub-networks extract features from two signatures, while the joining neuron measures the distance be(cid:173) tween the two feature vectors. Verification consists of comparing an extracted feature vector ~ith a stored feature vector for the signer. Signatures closer to this stored representation than a chosen thresh(cid:173) old are accepted, all other signatures are rejected as forgeries.

Cite

Text

Bromley et al. "Signature Verification Using a "Siamese" Time Delay Neural Network." Neural Information Processing Systems, 1993.

Markdown

[Bromley et al. "Signature Verification Using a "Siamese" Time Delay Neural Network." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/bromley1993neurips-signature/)

BibTeX

@inproceedings{bromley1993neurips-signature,
  title     = {{Signature Verification Using a "Siamese" Time Delay Neural Network}},
  author    = {Bromley, Jane and Guyon, Isabelle and LeCun, Yann and Säckinger, Eduard and Shah, Roopak},
  booktitle = {Neural Information Processing Systems},
  year      = {1993},
  pages     = {737-744},
  url       = {https://mlanthology.org/neurips/1993/bromley1993neurips-signature/}
}