IR+RGB Dataset for iBeta 1
12,000+ synchronized IR+RGB webcam recordings for iBeta Level 1 PAD testing
Check samples on Kaggle
Introduction
The IR + RGB Webcam Face Liveness Dataset provides a comprehensive solution for developing and validating presentation attack detection (PAD) systems in PC and web-based identity verification scenarios. With ISO/IEC 30107-3 compliance for iBeta Level 1 certification, this dataset enables researchers and security teams to build and pre-certify models that can effectively distinguish genuine users from paper-based presentation attacks during web-based onboarding and login sessions
Dataset summary
- 12,000+ synchronized video recordings capturing both infrared (IR) and RGB streams simultaneously
- 500+ unique participants providing diverse facial characteristics and demographics
- Dual-camera capture system with RGB and IR webcam sensors for multi-modal analysis
- Active liveness scenarios including head turns, movement patterns, and zoom interactions
- Four distinct paper-based attack types: Print cut (printed faces with cutouts), Cylinder (curved prints), On Actor (flat paper masks worn by actors), and 3D (volumetric paper masks)
- Diverse recording locations: 3 environments (60-80 different backgrounds)
- Comprehensive lighting conditions: natural and artificial lighting; additional warm/cold temperature variations
Source and collection methodology
The videos capture realistic spoofing conditions using IR and RGB webcams in desktop environments across 2 office spaces and 1 apartment. Attack materials were created using pigment printing on matte paper with special reflective ink designed for IR detection testing. Additionally, each video incorporates active liveness elements such as head movements and zoom-in/zoom-out effects, simulating real-world web-based verification interactions
Use cases and applications
iBeta Level 1 Certification Compliance:
- Helps to train the models for iBeta level 1 certification tests
- Allows pre-certification testing to assess system performance before submission
Inhouse Liveness Detection Models:
- Used for training and validation of anti-spoofing models
- Enables testing of existing algorithms and identification of their vulnerabilities against spoofing attacks
Who is this for?
- AI/ML teams – Train custom anti-spoofing models for security applications
- Identity verification providers – Ensure fraud prevention in KYC & financial services
- Financial institutions – Implement internal e-KYC solutions
File format and accessibility
- Format: Videos are optimized for compatibility with mainstream ML frameworks
- Resolution and frame rate: Videos are high-resolution with frame rates calibrated for capturing quick and realistic mask placements, ensuring precise data for model training
Potential customisation options:
- Filming videos attacks with targeted movements (E.g. – Zoom In / Zoom Out)
- Filming videos attacks for you on target devices (for example, webcams)
- Using your SDK for custom attack scenarios spoofing your ML model
- Use RGB and USB cameras to support diverse research and testing needs
Legal & Compliance
We prioritize data privacy, ethical AI development, and regulatory compliance. Our IR+RGB Dataset is collected and processed in full accordance with global data protection standards including GDPR, ensuring legality, security, and responsible AI practices
Sample dataset
A sample version of this dataset is available on Kaggle. Leave a request for additional samples in the form below
Contact us
Tell us about yourself, and get access to free samples of the dataset
