Online signature verification using signature down-sampling and signer-dependent sampling frequency

Mohammad Saleem,Bence Kovari

doi:10.1007/s00521-021-06536-z

Abstract

AbstractOnline signature verification considers signatures as time sequences of different measurements of the signing instrument. These signals are captured on digital devices and therefore consist of a discrete number of samples. To enrich or simplify this information, several verifiers employ resampling and interpolation as a preprocessing step to improve their results; however, their design decisions may be difficult to generalize. This study investigates the direct effect of the sampling rate of the input signals on the accuracy of online signature verification systems without using interpolation techniques and proposes a novel online signature verification system based on a signer-dependent sampling frequency. Twenty verifier configurations were created for five different public signature databases and a variety of popular preprocessing approaches and evaluated for 20–40 different sampling rates. Our results show that there is an optimal range for the sampling frequency and the number of sample points that minimizes the error rate of a verifier. A sampling frequency range of 15–50 Hz and a signature point count of 60–240 provided the best accuracies in our experiments. As expected, lower ranges showed inaccurate results; interestingly, however, higher frequencies often decreased the verification accuracy. The results show that one can achieve better or at least the same verification accuracies faster by down-sampling the online signatures before further processing. The proposed system achieved competitive results to state-of-the-art systems for different databases by using the optimal sampling frequency. We also studied the effect of choosing individual sampling frequencies for each signer and proposed a signature verification system based on signer-dependent sampling frequency. The proposed system was tested using 500 different verification methods and improved the accuracy in 92% of the test cases compared to the usage of the original frequency.

Highlights

Signature verification is one of the oldest biometric verification methods with strong legal support and wide usage including bank checks, writer identification, face recognition, medical detection, and a wide range of other applications [6, 24, 31]
This study investigates the direct effect of the sampling rate of the input signals on the accuracy of online signature verification systems without using interpolation techniques and proposes a novel online signature verification system based on a signer-dependent sampling frequency
Our results show that there is an optimal range for the sampling frequency and the number of sample points that minimizes the error rate of a verifier

Summary

Introduction

Signature verification is one of the oldest biometric verification methods with strong legal support and wide usage including bank checks, writer identification, face recognition, medical detection, and a wide range of other applications [6, 24, 31]. Automated signature verification has been in the focus of researchers for several decades. We can create systems that reach impressive error rates on different benchmark databases; the Budapest University of Technology and Economics, Budapest, Hungary possibilities for further improving these systems are always an open question [4]. We discuss a specific aspect of online signatures that may allow researchers to make better choices when designing new verification systems or to improve existing ones. The capturing typically happens at frequencies between 75 and 200 Hz. The aim of this work was to study the direct effect of the sampling frequency and the number of sample points on a simple signature verification system. One of the expectations was that the error rate would decrease when the sampling frequency increases because more points should provide more information about the signatures.

Objectives

Methods

Results

Conclusion