1993/08/01 by JANE BROMLEY, JAMES W. BENTZ, LÉON BOTTOU +5 · 1,400 citations
paper · doi:10.1142/s0218001493000339
published in International Journal of Pattern Recognition and Artificial Intelligence 07(04), 669-688 (World Scientific Pub Co Pte Lt)
crossref issued 1993/08/01 · crossref published 1993/08/01 · crossref published-print 1993/08/01 · crossref created 2004/11/22 · crossref published-online 2011/11/21 · crossref deposited 2019/08/06 · crossref indexed 2026/08/06
This paper describes the development of an algorithm for verification of signatures written on a touch-sensitive pad. The signature verification algorithm is based on an artificial neural network. The novel network presented here, called a “Siamese” time delay neural network, consists of two identical networks joined at their output. During training the network learns to measure the similarity between pairs of signatures. When used for verification, only one half of the Siamese network is evaluated. The output of this half network is the feature vector for the input signature. Verification consists of comparing this feature vector with a stored feature vector for the signer. Signatures closer than a chosen threshold to this stored representation are accepted, all other signatures are rejected as forgeries. System performance is illustrated with experiments performed in the laboratory.