3D:2D Profile Pic - Matching Guide

Please read the Intro to 3D Face Matching before getting started with Matching.

FaceTec's 3D to 2D Profile Pic Matching API is designed to Match 3D FaceMaps against Social Media and Dating App style images. This API is highly useful for these use cases as it allows you to add Profile Pic style images to the "trust chain".

By performing a 3D Liveness Check first, then comparing the Live Human that scanned their Face to User-uploaded profile images, you can ensure that Users are not misrepresenting themselves in their profiles.

Stopping Catfishing Users from misrepresenting their identities is an optimal use case for the 3D:2D Profile Pic API.

Important Note: The 3D:2D Profile Pic APIs should only be used against 2D Images from Social Media, Dating Apps, or 2D Photos of a similar style. For different scenarios, ensure you are using the proper APIs and are parsing the recommended data for optimal results. See the Security & Use Cases guide for more details.

Performance

This API returns Match Levels up to 99.999% (i.e. FARs up to 1 in 100,000 @ <1% FRR).

Get Started: 3D:2D Profile Pic API

This API requires a 3D FaceMap that has Proven Liveness. Once you have created one of these, call the 3D to 2D Profile Pic FaceTec Server API with the 3D FaceMap and the 2D Image. This API uses an externalDatabaseRefID to store and look up an Enrolled User's 3D FaceMap.

Please Note: The externalDatabaseRefID is 100% controlled by your business logic and code. FaceTec does not set this internally (but we do demonstrate how to set it in our samples). Setting & Retrieving the externalDatabaseRefID should be done in Server-Side Code, not your Device-Side code.

3D:2D Profile Pic Matching Technical Reference

See the Comprehensive API Reference for information about calling the FaceTec SDK APIs to perform a 3D to 2D Profile Pic Matching.

 

Match Levels

For 3D:2D Profile Pic Matching, Match Levels 0 through 6 are returned at 1% FRR.

  • Match Level 6 - 99.999% (1/100,000 FAR)

  • Match Level 5 - 99.99% (1/10,000 FAR)

  • Match Level 4 - 99.99% (1/1,000 FAR)

  • Match Level 3 - 99.8% (1/500 FAR)

  • Match Level 2 - 99.6% (1/250 FAR)

  • Match Level 1 - 99% (1/100 FAR)

  • Match Level 0 - Non-match
     

Factors Influencing Performance

This API will achieve the above Match Levels at low FRRs with good input data. Here are some factors that can negatively impact performance:

  • Image alterations: filters, face morphing, compression, upscaling, and re-saving.

  • Extreme pose variations.

  • Low resolution, blurry, or otherwise low-quality images.

  • Matching against Users wearing sunglasses is not supported.

  • Group photos - if multiple faces are found, the highest Matching face result will be returned. Images with more than 4 faces will be rejected.

  • Conditions like extreme lighting, exaggerated facial expressions, or artistic alterations of the face.

  • Homogeneous datasets, matching with close relatives, and contrived testing with look-alikes.