The Open UniversitySkip to content
 

Signature verification using a Siamese time delay neural network

Bromley, Jane M.; Guyon, Isabelle; LeCun, Yann; Sackinger, Eduard and Shah, Roopak (1994). Signature verification using a Siamese time delay neural network. In: 7th Annual Neural Information Processing Systems Conference, 29 Nov - 02 Dec 1993, Denver, Morgan Kaufmann Publishers, pp. 737–744.

Full text available as:
Full text not publicly available (Version of Record)
Due to publisher licensing restrictions, this file is not available for public download
URL: http://books.nips.cc/papers/files/nips06/0737.pdf
Google Scholar: Look up in Google Scholar

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 outputs. During training the two sub-networks extract features from two signatures, while the joining neuron measures the distance between the two feature vectors. Verification consists of comparing an extracted feature vector with a stored feature vector for the signer. Signatures closer to this stored representation than a chosen threshold are excepted, all other signatures are rejected as forgeries.

Item Type: Conference or Workshop Item
Copyright Holders: 1994 American Telephone and Telegraph Company
ISBN: 1-55860-322-0, 978-1-55860-322-6
Extra Information: Advances in Neural Information Processing Systems 6
Edited by Jack D. Cowan, Gerald Tasauro, Joshua Alspector
Keywords: "Siamese" neural network; TDNN; time delay neural network
Academic Unit/School: Faculty of Science, Technology, Engineering and Mathematics (STEM) > Computing and Communications
Faculty of Science, Technology, Engineering and Mathematics (STEM)
Related URLs:
Item ID: 39214
Depositing User: Jane M. Bromley
Date Deposited: 09 Jan 2014 10:57
Last Modified: 08 Dec 2018 17:30
URI: http://oro.open.ac.uk/id/eprint/39214
Share this page:

Actions (login may be required)

Policies | Disclaimer

© The Open University   contact the OU