Skip to content
Snippets Groups Projects
filelist-guide.rst 7.15 KiB

Verification File List Database Guide

The Database Interface

The :py:class:`bob.bio.base.database.FileListBioDatabase` complies with the standard biometric verification database as described in :ref:`bob.bio.base`. All functions defined in that interface are properly instantiated, as soon as the user provides the required file lists.

Creating File Lists

The initial step for using this package is to provide file lists specifying the 'world' (training; optional), 'dev' (development; required) and 'eval' (evaluation; optional) set to be used by the biometric verification algorithm. The summarized complete structure of the list base directory (here denoted as basedir) containing all the files should be like this:

filelists_directory
     |-- norm
           |-- train_world.lst
           |-- train_optional_world_1.lst
           |-- train_optional_world_2.lst
     |
     |-- dev
           |-- for_models.lst
           |-- for_probes.lst
           |-- for_scores.lst
           |-- for_tnorm.lst
           |-- for_znorm.lst
     |
     |-- eval
           |-- for_models.lst
           |-- for_probes.lst
           |-- for_scores.lst
           |-- for_tnorm.lst
           |-- for_znorm.lst

The file lists contain several information that need to be available for the biometric recognition experiment to run properly. A complete list of possible information is:

  • filename: The name of the data file, relative to the common root of all data files, and without file name extension.
  • client_id: The name or ID of the subject the biometric traces of which are contained in the data file. These names are handled as :py:class:`str` objects, so 001 is different from 1.
  • model_id:
    • used for model enrollment: The name or ID of the client model that should be enrolled. In most cases, the model_id is identical to the client_id.
    • used for scoring: The name or ID of the client model that the probe file should be compared with.
  • claimed_client_id:
    • used for scoring: The client_id of the client model that the probe file should be compared with.