Neural network modelling of kinematic and dynamic features for signature verification

TL;DR

This paper compares physical and neural network methods for estimating kinematic and dynamic features in signature verification, demonstrating neural networks' effectiveness and generalization across multiple datasets.

Contribution

It introduces a neural network approach for estimating signature dynamic features, offering a cost-effective alternative to physical measurement methods.

Findings

Neural network can effectively estimate signature dynamic parameters.

The model generalizes well across multiple signature datasets.

Neural approach matches physical measurement accuracy.

Abstract

Online signature parameters, which are based on human characteristics, broaden the applicability of an automatic signature verifier. Although kinematic and dynamic features have previously been suggested, accurately measuring features such as arm and forearm torques remains challenging. We present two approaches for estimating angular velocities, angular positions, and force torques. The first approach involves using a physical UR5e robotic arm to reproduce a signature while capturing those parameters over time. The second method, a cost effective approach, uses a neural network to estimate the same parameters. Our findings demonstrate that a simple neural network model can extract effective parameters for signature verification. Training the neural network with the MCYT300 dataset and cross validating with other databases, namely, BiosecurID, Visual, Blind, OnOffSigDevanagari 75 and OnOffSigBengali 75 confirm the models generalization capability.