Coverage for src/bob/pad/face/config/swan.py: 100%

1"""The Swan_ Database. 

2 

3To configure the location of the database on your computer, run:: 

4 

5 bob config set bob.db.swan.directory /path/to/database/swan 

6 

7 

8The Idiap part of the dataset comprises 150 subjects that are captured in six 

9different sessions reflecting real-life scenarios of smartphone assisted 

10authentication. One of the unique features of this dataset is that it is 

11collected in four different geographic locations representing a diverse 

12population and ethnicity. Additionally, it also contains a multimodal 

13Presentation Attack (PA) or spoofing dataset using low-cost Presentation Attack 

14Instruments (PAI) such as print and electronic display attacks. The novel 

15acquisition protocols and the diversity of the data subjects collected from 

16different geographic locations will allow developing a novel algorithm for 

17either unimodal or multimodal biometrics. 

18 

19PAD protocols are created according to the SWAN-PAD-protocols document. 

20Bona-fide session 2 data is split into 3 sets of training, development, and 

21evaluation. The bona-fide data from sessions 3,4,5,6 are used for evaluation as 

22well. PA samples are randomly split into 3 sets of training, development, and 

23evaluation. All the random splits are done 10 times to created 10 different 

24protocols. The PAD protocols contain only one type of attacks. For convenience, 

25PA_F and PA_V protocols are created for face and voice, respectively which 

26contain all the attacks. 

27""" 

28from bob.pad.face.database import SwanPadDatabase 

29 

30database = SwanPadDatabase()