Handwritten Signature and Text based User Verification using Smartwatch

Wrist-wearable devices such as smartwatch hardware have gained popularity as they provide quick access to various information and easy access to multiple applications. Among the numerous smartwatch applications, user verification based on the handwriting is gaining momentum by considering its reliability and user-friendliness. In this paper, we present a novel technique for user verification using a smartwatch based writing pattern or style. The proposed approach leverages accelerometer data captured from the smartwatch that is further represented using 2D Continuous Wavelet Transform (CWT) and deep features extracted using the pre-trained ResNet50. These features are classified using an ensemble of classifiers to make the final decision on user verification. Extensive experiments are carried out on a newly captured dataset using two different smartwatches with three different writing scenarios (or activities). Experimental results provide critical insights and analysis of the results in such a verification scenario.

I. Introduction

Handwritten text or signature-based user authentication has been extensively studied over the past 50 years. Several applications have been deployed to verify the handwritten text in the context of traditional payment systems and automated cheque authorization for authenticating the user. The conventional handwritten text verification systems employ additional hardware, for instance, to digitize the handwritten signature demanding extra digitizing unit. In the second generation of the same systems, the online handwritten signature was introduced, which leverages the pressure and the location while writing. Despite the promising performance of the conventional handwritten techniques in both generations, the need for extra equipment to perform reliable verification is inevitable. Such limits restrict the traditional handwritten verification's applicability, especially where the service provider is forced to invest in additional hardware or equipment.