Face Match 1:1
Didit's Face Match 1:1 solution provides enterprise-grade biometric verification through advanced computer vision and machine learning algorithms. Our system achieves 99.9% accuracy with a false acceptance rate (FAR) of less than 0.1%.

Key Features
Advanced Facial Comparison
- Deep neural network architecture
- 68-point facial landmark detection
- Advanced feature extraction
- Cross-demographic performance testing
High Accuracy
- 99.9% accuracy in controlled environments
- Robust to pose, lighting, and aging variations
- False acceptance rate (FAR) of less than 0.1%
- Continuous algorithm improvements
Face Recognition
- Advanced facial comparison algorithms
- Similarity scoring from 0-100%
- Configurable matching thresholds
- Compatible with global ID document types
Configurable Thresholds
You can customize security levels by setting different thresholds for face matching scores. For example:

These thresholds can be adjusted based on your risk tolerance and security requirements.
How It Works
Image Preparation
Different workflows handle image selection in unique ways:
-
ID Verification Based Workflow
- Automatically selects best quality image from liveness check
- Pairs selected image with photo from ID document
- Ensures consistent quality between both images
-
Biometric Authentication Based Workflow
- Takes new live photo from user
- Retrieves stored reference photo from previous approved liveness check
- Compares images to confirm identity
-
Face Match API
- Accepts direct upload of two images
- Requires one live capture photo
- Requires one reference photo for comparison
- Validates image quality before processing
All images undergo preprocessing:
- Resolution and lighting normalization
- Face detection and alignment
- Image quality enhancement
- Strict quality validation checks
Face Matching
- Compares the verified live image and the ID document photo
- Analyzes 68 facial landmarks for precise alignment
- Generates a similarity score from 0-100%
- Applies configured thresholds for automated decisions
Result Processing
- System applies your configured thresholds
- Automatically approves, declines, or flags for review
- Results available via API, dashboard, or webhooks
- Detailed metrics and confidence scores provided