Performance evaluation of handwritten signature recognition in mobile environments

Abstract

The utilisation of biometrics in mobile scenarios is increasing remarkably. At the same time, handwritten signature recognition is one of the modalities with highest potential of use for those applications where customers are used to sign in those traditional processes. However, several improvements have to be made in order to reach acceptable levels of performance, reliability and interoperability. The evaluation carried out in this study contributes with multiple results obtained from 43 users signing 60 times, divided in three sessions, in eight different capture devices, being six of them mobile devices and the other two digitisers specially made for signing and used as a baseline. At each session, a total of 20 signatures per user are captured by each device, so that the evaluation here reported a total of 20 640 signatures, stored in ISO/IEC 19794-7 format. The algorithm applied is a DTW-based one, particularly modified for mobile environments. The results analysed include interoperability, visual feedback and modality tests. One of the big challenges of this research was to discover if the handwritten signature modality in mobile devices should be split into two different modalities, one for those cases when the signature is performed with a stylus, and another when the fingertip is used for signing. Many relevant conclusions have been collected and, over all, multiple improvements have been reached contributing to future deployments of biometrics in mobile environments.

Automatic usability and stress analysis in mobile biometrics

“…There are previous relevant studies in the literature about handwritten signature recognition in mobile devices [17] [18] and there are also commercial products using these kinds of algorithms [19]. Works previously carried out by authors regarding usability show interesting outcomes that have been applied to this experiment.…”

Optimal feature selection and inter-operability compensation for on-line biometric signature authentication

“…So, in this experiment we can conclude that training and testing with different devices has a big impact in the performance, and the critical case is when the quality of the device used for testing is worse than the quality of the device used for training. The performance of the system in an inter-operability case has been studied in recent works for random forgeries cases [2], but not proposing any system which compensates the inter-operability between different quality devices. For this reason, the aim of the next experiments is to obtain an optimal feature vector which works satisfactory for all the cases at the same time.…”

“…For example, due to the increasing deployment of smartphones in the commercial sector to facilitate payments, people can access an application with different devices [17]. For all these reasons, the main goal of this work is to study the performance of the system in an inter-operable case for dynamic signature verification since there are very few works regarding this subject [1,2]. In addition, it is important to note that the systems used in these related works do not take into account the inter-operability problem in the development phase.…”

User acceptance of planar semiconductor fingerprint sensors

“…Biometric recognition systems are already deployed in several scenarios of our daily life such as access controls in airports or offices, gyms and even in smartphones (not only to unlock them but for common procedures such as signing documents [1] or web access). Therefore they are being used very frequently and are being part of people routines.…”

“…Therefore, testing the user acceptance is indispensable when designing biometric systems but it is not carried out in all cases involving many times the disuse of the technology. Some of the main concerns expressed by users to not use biometric recognition are suspicion, invasion of privacy, fear of damage or linking biometrics with personal data, apprehension of "it won't work for me" and many others [1] [2].…”