iSignDB: A biometric signature database created using smartphone

Citation Author(s):
Jamia Millia Islamia
Jamia Millia Islamia
Jamia Millia Islamia
Farhana Javed
Jamia Millia Islamia
Submitted by:
Suraiya Jabin
Last updated:
Sat, 10/31/2020 - 05:08
Data Format:
0 ratings - Please login to submit your rating.


iSignDB: A biometric signature database created using smartphone

Suraiya Jabin, Sumaiya Ahmad, Sarthak Mishra, and Farhana Javed Zareen

Department of Computer Science, Jamia Millia Islamia, New Delhi-110025, India

It's a database of biometric signatures recorded using sensors present in a smartphone. ​The dataset iSignDB is created to implement a novel anti-spoof biometric signature authentication for smartphone users.

  • We named it iSignDB as we collected it using a licensed MathWorks cloud account and with iOS and Android based smartphone devices (iPhone 7 Plus and Redmi Note 7) for capturing dynamic signatures.
  • A total of 48 subjects volunteered for data collection out of which we identified 32 users as genuine signature contributors and 16 users as fake signature contributors with skilled forgery.
  • Data was collected in 3 different sessions separated by at least 20 days in order to capture the emotional intelligence of users.
  • During each session, one pair of subjects, out of which one subject contributed 10 original signatures and the other contributed 5 fake signatures.
  • For obtaining a fake signature, a subject was allowed to practice copying not only the signature image of a genuine user but also the behaviorism (e.g. number of touchpoints, style of finger movement while signing, etc.) while genuine signer signs on the touch screen of a smartphone.
  • A total of 30 genuine and 15 fake samples were collected for each of 32 users.
  • One sign of a user contains a sensor log captured using sensors present in the smartphone: Accelerometer, Gyroscope, Magnetometer, and GPS, etc along with images of signature as obtained by performing a sign on the touch screen of the device.
  • We have uploaded the smartphone biometric sign database of all 32 users in this repository. The full database of 32 users is available for other researchers only after they sign and submit the terms and conditions of using it.
  • We successfully trained 32 BiGRU models on dynamic signature dataset created with EER of 0.66% which is a significant improvement.
  • We provide Matlab code (compatible with MATLAB 2020a licensed version) for training, testing, and calculating EER in this repository (
  • iSignDB is available to other researchers only after signing its "Term of use" agreement and acknowledging it properly in their work.
  • Nomenclature for files in the dataset iSignDB: (each sign with 5 sensor logs corresponding to Acceleration, Angular Velocity, Magnetic Field, Orientation, and Position, and image of signature

u01_s3_r010_AngVel.txt : means a signature of user 1, on session 3, real signature, 10th sample’s Angular velocity sensor log

u01_s1_f02_MagField.txt : means a signature of user 1, on session 1, fake signature, 2nd sample’s magnetic field sensor log

u01_s1_r01_im.png : image of the genuine signature of user 1, captured on session 1, sample 1


Terms of Use for iSignDB Dataset

 1. Definitions

 The following terms, unless the context requires otherwise, have the following meanings:

 “Data Team”: means Prof. Suraiya Jabin of JMI, her Ph.D. students (Ms. Sumaiya Ahmad and Mr. Sarthak Mishra), and MCA students at the Department of Computer Science, JMI who worked on the iSignDB dataset;

 “iSignDB Dataset”: means the large-scale data set about dynamic signature performed using smartphone collected by the Data Team;

 “Licensee”, “You”, “Your”, “Yours”: means the person or entity acquiring a license hereunder for access to and use of the iSignDB Dataset.

 2. Grant of License

 Prof. Suraiya Jabin of JMI hereby grants to You a non-exclusive, non-transferable, revocable license to use the iSignDB Dataset solely for Your non-commercial, educational, and research purposes only, but without any right to copy or reproduce, publish or otherwise make available to the public or communicate to the public, sell, rent or lend the whole or any constituent part of the iSignDB Dataset thereof. The iSignDB Dataset shall not be redistributed without the express written prior approval of the Prof. Suraiya Jabin of JMI. You agree to respect the privacy of those human subjects whose smartphone usage behavior data are included in the iSignDB Dataset. Do not attempt to reverse the anonymization process to identify specific identifiers including, without limitation, names, postal address information, telephone numbers, e-mail addresses, social security numbers, and biometric identifiers. You agree not to reverse engineer, separate or otherwise tamper with the iSignDB Dataset so that data can be extracted and used outside the scope of that permitted in this Agreement. 

 You agree to acknowledge the source of the iSignDB Dataset in all of Your publications and presentations based wholly or in part on the iSignDB Dataset. You agree to provide a disclaimer in any publication or presentation to the effect that the Prof. Suraiya Jabin of JMI does not bear any responsibility for Your analysis or interpretation of iSignDB Dataset.  

 You agree and acknowledge that the Prof. Suraiya Jabin of JMI may hold, process, and store any personal data submitted by You for validation and statistical purposes and for the purposes of the administration and management of iSignDB Dataset. You agree that any personal data submitted by You is accurate to the best of his or her knowledge.

 Prof. Suraiya Jabin provides the iSignDB Dataset "AS IS," without any warranty or promise of technical support, and disclaims any liability of any kind for any damages whatsoever resulting from use of the ISIGNDB Dataset.

 After acquiring the license of the iSignDB database, user is requested to delete the database after 2 years. If a user wishes to use it after 2 years, he/she will need to acquire the license again.


 Your acceptance and use of the iSignDB Dataset binds you to the terms and conditions of this License as stated herein.



Very interesting! 

I'd love to try an algorithm I designed for motion-based identification on this data -- can I accept the terms of service and get access?



-- Sam Heiserman

Submitted by Sam Heiserman on Fri, 05/29/2020 - 16:07

Dear Dr. Sam Heiserman,

thank you for your interest!

Our work based on this dataset is under review in a good journal. As soon as this work gets published in some desired journal, we will make it available after acceptance of its term of use.


Best regards


Submitted by Suraiya Jabin on Tue, 06/02/2020 - 23:40