BiDA logo Biometrics and Data Pattern Analytics - BiDA Lab EPS logo UAM logo

Please note the license must be signed by a permanent faculty or research member from your university, and a scanned copy must be attached to the application.


  1. Download license agreement, send by email one signed and scanned copy to according to the instructions given in point 2.

  2. Send an email to, as follows:
    Subject: [CODE download: TouchDB_ Benchmark]

    : Your name, e-mail, telephone number, organization, postal mail, purpose for which you will use the database, time and date at which you sent the email with the signed license agreement.

  3. Once the email copy of the license agreement has been received at ATVS, you will receive an email with a username, a password, and a time slot to download the benchmark.

  4. Download the benchmark, for which you will need to provide the authentication information given in step 4. After you finish the download, please notify by email to that you have successfully completed the transaction.

  5. For more information, please contact:


This Matlab code includes the algorithms necessary to reproduce the benchmark evaluated in [1]. The benchmark is composed by: 1) Experiments with statistical and discriminative methods for touch biometrics, including a novel architecture that independently processes touch patterns of different orientation; 2) the contents of four touchscreen biometrics databases [2-5].

Figure 1 shows the architecture of the two methods evaluated based on SVM and GMMs. For further information on the methods, we refer the reader to [1].

Architecture of the touch biometrics authentication schemes studied.

Figure 1. Architecture of the touch biometrics authentication schemes studied.


  1. Copy the databases in their respective folders according to the instructions included in each folder.

  2. Execute main.m and follow the instructions.


For further information on the benchmark and databases, we refer the reader to [1-5].

  • [1] J. Fierrez, A. Pozo, M. Martinez-Diaz, J. Galbally and A. Morales, "Benchmarking Touchscreen Biometrics for Mobile Authentication", IEEE Trans. on Information Forensics and Security, vol. 13, n. 11, pp. 2720-2733, November, 2018. [PDF]

  • [2] M. Frank, R. Biedert, E. Ma, I. Martinovic, and D. Song, “Touchalytics: On the applicability of touchscreen input as a behavioral biometric for continuous authentication,” IEEE Transactions on Information Forensics and Security, vol. 8, no. 1, pp. 136–148, 2013.

  • [3] M. Antal, Z. Bokor, and L. Z. Szab´o, “Information revealed from scrolling interactions on mobile devices,” Pattern Recognition Letters, vol. 56, pp. 7–13, April, 2015.

  • [4] A. Serwadda, V. V. Phoha, and Z. Wang, “Which verifiers work?: A benchmark evaluation of touch-based authentication algorithms,” in Proc. IEEE BTAS, 2013.

  • [5] U. Mahbub, S. Sarkar, V. M. Patel, and R. Chellappa, “Active user authentication for smartphones: A challenge data set and benchmark results,” in Proc. IEEE BTAS, 2016.

Please remember to reference [1] on any work made public, whatever the form, based directly or indirectly on any part of the data and code provided. Please also cite [2-5] depending on the particular swipe dataset used.


  • The acquisition of this database has been supported by projects: COGNIMETRICS (TEC2015-70627-R MINECO/FEDER), IJCI-2015-24742 (MINECO/FEDER), and Cecabank. The work of J. Fierrez was supported by the Imperial College London under Grant PRX16/00580.