The objective of this paper is twofold. First, it presents an experimental investigation on stability of dynamic signatures. For the purpose, a well-suited index for estimating local stability is considered, based on a multiple matching strategy performed by Dynamic Time Warping. Second, the stability index is used to estimate local stability of dynamic signatures in different representation domains and to select the most profitable domain for automatic signature verification. The experimental results demonstrate the effectiveness of the new approach in estimating personal stability is signing and its utility in selecting the most profitable representation domain for signature verification.
Stability Analysis of Dynamic Signatures in Multiple Representation Domains: Application to Automatic Signature Verification
PIRLO, Giuseppe;IMPEDOVO, DONATO
2014-01-01
Abstract
The objective of this paper is twofold. First, it presents an experimental investigation on stability of dynamic signatures. For the purpose, a well-suited index for estimating local stability is considered, based on a multiple matching strategy performed by Dynamic Time Warping. Second, the stability index is used to estimate local stability of dynamic signatures in different representation domains and to select the most profitable domain for automatic signature verification. The experimental results demonstrate the effectiveness of the new approach in estimating personal stability is signing and its utility in selecting the most profitable representation domain for signature verification.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.