DeepSignDB: Deep On-Line Signature Verification Database (DeepSignDB)
Handwriting; On-Line Signature; Biometrics; Deep Learning
Download instructions available at https://github.com/BiDAlab/DeepSignDB
The DeepSignDB database comprises a total of 1526 users from four different popular databases and a novel signature database not presented yet, named e-BioSign DS2. The following image graphically summarises the design, acquisition devices, and writing tools considered in the DeepSignDB database.
Description of the design, acquisition devices, and writing tools considered in the new DeepSignDB database. A total of 1526 users and 8 different captured devices are used (5 Wacom and 3 Samsung general purpose devices). For the Samsung devices, signatures are also collected using the finger. Gen. Sig. = Genuine Signatures, and Sk. Forg. = Skilled Forgeries.
R. Tolosana, R. Vera-Rodriguez, J. Fierrez and J. Ortega-Garcia, "DeepSign: Deep On-Line Signature Verification", IEEE Transactions on Biometrics, Behavior, and Identity Science, 2021
- DeepSignDB: Deep On-Line Signature Verification Database v.1