How to participate this challenge and dataset download. It includes three steps below:
Register for one of challenges at CVPR workshop 2020 below:
Track 1 Chalearn Multi-modal Cross-ethnicity Face anti-spoofing Recognition Challenge (link).
Track 2 Chalearn Single-modal (RGB) Cross-ethnicity Face anti-spoofing Recognition Challenge (link).
2. In track 1 or 2, it will tell you how to download the CASIA-SURF CeFA dataset (you will be asked to sign an agreement).
Note: We use the same data in both track 1 and 2. Therefore, you can apply the CASIA-SURF CeFA dataset in one of both tracks.
3. You will be required to first sign a licensing agreement and send it to: Jun Wan, jun.wan@ia.ac.cn .
Notes： If you tend to get the commercial license of this dataset, please email to contact@surfingtech.cn
Q&A
Q: Fine-grained spoof labels
A: For the CASIA-SURF CeFA dataset, it includes three ethnicities.
Three ethnicity data format: Race/Race-ID-IdCard/Race_ID_AcqDevice_Session_PAI
P1: Race: 1:AF 2:CA 3:EA
P2: ID: 000-599
P3: AcqDevice: 1:rssdk 2:mp4 3:bag 4:MOV
P4: Session(environment): 1:indoor 2:outdoor 3:random
P5: PAI: 1:Real 2:Cloth 3:Pic(phtoto) 4:Screen
Example: EA/EA-012-198006250024/1_000_1_1_1 (P1_P2_P3_P4_P5)
3D-Mask Format: 3D-Mask/ID/3DMASK_ID_If-Dresses_If-Glasses_AcqDevice_Session_AttackType
P0: 3DMASK: 1
P1: ID:002-100
P2: If-Dresses: 0:No_Dresses 1:Dresses
P3: If-Glasses: 0:No_Glasses 1:Glasses
P4: AcqDevice: 1:Camera 2:D435i
P5: Session(environment): 1:Indoor 2:Outdoor
P6: AttackType(environment): 1:NoLighting 2:BackLighting 3:AlongLighting 4:SideLighting
Example: 3D-MASK/ID/3DMASK_ID_Dresses_Glasses_D435i_Indoor_AlongLighting (3D-MASK/002/1_002_1_1_2_1_3)
Silicione-Mask format: Silicone-Mask/ID/SiliconeMask_ID_Dresses_If-Glasses_AcqDevice_Session_AttackType
P0: SiliconeMask: 2
P1: ID: 001-008
P2: Dresses: 1:Dresses
P3: If-Glasses: 0:No_Glasses 1:Glasses
P4: AcqDevice: 1:Camera 2:D435i
P5: Session(environment): 1:Indoor
P6: AttackType(environment): 1:NoLighting 2:BackLighting 3:AlongLighting 4:SideLighting