Face Anonymizer


The Face Anonymizer is a facial blurring algorithm designed to consistently remove identifying features. It can be used in real-time, ensuring absolute compliance with GDPR regulation, or on video footage before public release. The algorithms parameters are easily customizable according to project needs and local legislation.



CVEDIA | Face AnonymizerCVEDIA | Face AnonymizerCVEDIA | Face AnonymizerCVEDIA | Face AnonymizerCVEDIA | Face AnonymizerCVEDIA | Face Anonymizer



PERFORMANCE

Optimized for edge performance with a low power profile.

PERSPECTIVE

Ground-to-ground.

CONDITIONS

Dawn to dusk and artificial lighting.

ENVIRONMENT

Environmentally agnostic performance.

ARCHITECTURE

Backbone: Resnet-101; Detector: RefineDet.

FUNCTIONALITY

Detection.

INPUT SIZE

512x512.

SENSOR MODALITY

Visible light.



Want to see our AI in action?

Book a demo now →



Our services


  • MAINTENANCE

Each CVEDIA model comes backed with an ongoing maintenance agreement. Our team is available for continuous improvements and to ensure upkeep.


  • FINE GRAIN CLASSIFICATION

Speak to our team to discuss model classification as a service add on or as a separate model. CVEDIA’s in-house team will work with you to define your requirements, and build a synthetic-based model incorporating your classification specifications.


  • ADDITIONAL CLASSES

CVEDIA models are built using proprietary synthetic data technology, meaning adding additional classes to your model is possible in a matter of weeks.

Use cases


  • GRPR COMPLIANCE

Ensure your machine learning application complies with GDPR legislation in real-time. The Face Anonymizer algorithm has a low power profile, making it simple to add to existing computing resources.


  • CHILD PRIVACY

This algorithm employs CVEDIA's synthetic technology to effectively anonymize children in live footage, making it possible to customize anonymization parameters in order to specifically blur faces resembling minors.