Face Anti-spoofing  (Presentation Attack Detection) Challenge@CVPR2020

How to participate this challenge and dataset download. It includes three steps 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