BioSecure Signature Evaluation Campaign 2011

  • Increase font size
  • Default font size
  • Decrease font size

Protocols and Tasks

Skilled forgeries categorized according to their quality

Using our Entropy-based forgery quality measure, skilled forgeries are categorized into 2 categories according to their quality and are labeled to be of « Bad » or « Good » quality. 

 

Evaluation protocols and tasks for participants

Generic Protocol for all tasks: for each person, 5 genuine signatures of Session 1 will be used as Reference Signatures. Testing will be carried out on the remaining 10 genuine signatures of Session 1 and 20 skilled forgeries acquired during both sessions, labeled according to their quality (as explained above).

Following the two main objectives of the ESRA, the Generic Protocol will be used by participants in two Evaluation Tasks:

- TASK 1, Evaluating the impact of forgery quality on systems’ performance and the impact of acquisition conditions on forgery quality :

  • Participants will use the Development Subsets DS2-50 and DS3-50;
  • Only pen coordinates will be considered in this task;
  • Participants will submit the most resistant system to attacks on DS2-50 and DS3-50 following the Generic Protocol.

EVALUATION PROTOCOL 1: The Organizer will test the submitted systems in this task on the whole DS2-382 and DS3-382 sequestered test subsets to study the impact of the mobile platform on system performance according to the Generic Protocol. 

 

- TASK 2Evaluating the impact of different time functions combinations on the resistance of signatures to attacks :

  • Participants will use only DS2 subset considering one of the three configurations of input time functions:

                -  Only pen coordinates. In this case, the associated Development Subset is DS2-50

                -  Pen coordinates and pen pressure. In this case, the associated Development Subset is DS2-50-1

                - All the five time functions. In this case, the associated Development Subset is DS2-50-2

  • Participants will submit the most resistant system to attacks following the Generic Protocol, considering as inputs only coordinates, or coordinates and pressure, or all the 5 time functions.

EVALUATION PROTOCOL 2: The Organizer will test the submitted system in this Task on the whole sequestered DS2-382 data set, taking into account the inputs considered by the participant, in order to study the influence of parameters on systems’ resistance to attacks, according to the Generic Protocol.