This paper describes the experimental framework and results of the ICDAR 2021 Competition on On-Line Signature Verification (SVC 2021). The goal of SVC 2021 is to evaluate the limits of on-line signature verification systems on popular scenarios (office/mobile) and writing inputs (stylus/finger) through large-scale public databases. Three different tasks are considered in the competition, simulating realistic scenarios as both random and skilled forgeries are simultaneously considered on each task. The results obtained in SVC 2021 prove the high potential of deep learning methods. In particular, the best on-line signature verification system of SVC 2021 obtained Equal Error Rate (EER) values of 3.33% (Task 1), 7.41% (Task 2), and 6.04% (Task 3). SVC 2021 will be established as an on-going competition, where researchers can easily benchmark their systems against the state of the art in an open common platform using large-scale public databases such as DeepSignDB and SVC2021_EvalDB, and standard experimental protocols.
@article{arxiv.2106.00739,
title = {ICDAR 2021 Competition on On-Line Signature Verification},
author = {Ruben Tolosana and Ruben Vera-Rodriguez and Carlos Gonzalez-Garcia and Julian Fierrez and Santiago Rengifo and Aythami Morales and Javier Ortega-Garcia and Juan Carlos Ruiz-Garcia and Sergio Romero-Tapiador and Jiajia Jiang and Songxuan Lai and Lianwen Jin and Yecheng Zhu and Javier Galbally and Moises Diaz and Miguel Angel Ferrer and Marta Gomez-Barrero and Ilya Hodashinsky and Konstantin Sarin and Artem Slezkin and Marina Bardamova and Mikhail Svetlakov and Mohammad Saleem and Cintia Lia Szücs and Bence Kovari and Falk Pulsmeyer and Mohamad Wehbi and Dario Zanca and Sumaiya Ahmad and Sarthak Mishra and Suraiya Jabin},
journal= {arXiv preprint arXiv:2106.00739},
year = {2021}
}