Universidad Autonoma de Madrid (SPAIN)
About this paper:
Appears in: EDULEARN15 Proceedings
Publication year: 2015
Pages: 5470-5476
ISBN: 978-84-606-8243-1
ISSN: 2340-1117
Conference name: 7th International Conference on Education and New Learning Technologies
Dates: 6-8 July, 2015
Location: Barcelona, Spain
Handwritten signatures are one of the most socially accepted biometric traits. Signatures are commonly used in financial and legal agreements since more than a century. In education, signatures are used for attendance control, either to lectures or exams, but not for (automatic) authentication. With the rapid deployment of dynamic signature recognition [1], this technology is ready to be used for student authentication. Also, the use of this technology can be extended to different administrative services within the education system, in order to add a higher security level to the traditional procedures of authentication (e.g., visually checking the face and/or signature on the person identity card).

Nowadays, signatures can be easily captured by means of electronic devices (e.g. pen tablets, PDAs, grip pens, smartphones, etc.) For this reason, the popularity of this biometric trait is rapidly increasing in the last few years. Even more, signatures can be made using the finger as the writing tool on smartphones [2]. In this paper, we will analyse two scenarios for student authentication using their signatures: i) an office scenario with a high quality pen tablet specifically designed to acquire signatures (i.e., Wacom device), and ii) a mobile scenario where users sign on their smartphones with the finger improving this way the usability. For this experimental study we make use of the e-BioSign database [3], which was captured using various modern pen tablet devices and smartphones. The database contains signatures from 70 users including students and educators, captured in two sessions in different days. The experiments on automatic authentication using dynamic signatures are conducted considering two different types of forgeries, namely: i) random forgeries (the case where an impostor uses his own signature claiming to be another person), and ii) skilled forgeries (where impostors imitate the signature of other persons).

Based on the experimental results in these scenarios, the paper will then discuss about practical implications of the application of automatic dynamic signature authentication in the academic environment.

[1] J. Fierrez and J. Ortega-Garcia, "On-line Signature Verification", A. K. Jain, A. Ross and P.Flynn (Eds.), Handbook of Biometrics, Springer, pp. 189-209, 2008.
[2] M. Martinez-Diaz, J. Fierrez and J. Galbally, "The DooDB Graphical Password Database: Data Analysis and Benchmark Results", IEEE Access, Vol. 1, pp. 596-605, 2013.
[3] R. Vera-Rodriguez, R. Tolosana, J. Ortega-Garcia and J. Fierrez, "e-BioSign: Stylus- and Finger-Input Multi-Device Database for Dynamic Signature Recognition", in Proc. 3rd International Workshop on Biometrics and Forensics (IWBF), IEEE Press, 2015
Innovation, person authentication, signature recognition, biometrics.