SVC-onGoing: Signature Verification Competition

• DOI: 10.48550/arxiv.2108.06090
• Publication Date: 2021-01-01
• Authors: Rubén Tolosana; Rubén Vera-Rodríguez; Carlos González‐G...; Julián Fiérrez; Aythami Morales; Javier Ortega-García; Juan Carlos Ruiz-...; Sergio Romero-Tap...; Santiago Rengifo; Miguel Caruana; Jiajia Jiang; Songxuan Lai; Lianwen Jin; Yecheng Zhu; Javier Galbally; Moises Díaz; Miguel A. Ferrer; Marta Gomez‐Barrero; Ilya Hodashinsky; Konstantin Sarin; Артем Слезкин; Marina Bardamova; Mikhail Svetlakov; Mohammad Saleem; Cintia Lia Szücs; Bence Kővári; Falk Pulsmeyer; Mohamad Wehbi; Dario Zanca; Sumaiya Ahmad; Sarthak Mishra; Suraiya Jabin
• Keywords: Signature (topology); Benchmark (surveying); Stylus

This article presents SVC-onGoing, an on-going competition for on-line signature verification where researchers can easily benchmark their systems against the state of art in open common platform using large-scale public databases, such as DeepSignDB and SVC2021_EvalDB, standard experimental protocols. SVC-onGoing is based on ICDAR 2021 Competition On-Line Signature Verification (SVC 2021), which has been extended to allow participants anytime. The goal evaluate limits popular scenarios (office/mobile) writing inputs (stylus/finger) through databases. Three different tasks are considered competition, simulating realistic both random skilled forgeries simultaneously each task. results obtained prove high potential deep learning methods comparison with traditional methods. In particular, best system Equal Error Rate (EER) values 3.33% (Task 1), 7.41% 2), 6.04% 3). Future studies field should be oriented improve performance challenging mobile several devices finger used during acquisition.