2D:2D Matching

The FaceTec 2D:2D Matching Algorithms can achieve a FAR of 1 in 100,000 and a FRR less than 0.99%. Match Levels correspond to the probabilities that a given pair of samples is the same person.


2D:2D Matching

2D:2D Matching is used to determine if two facial images match.

To learn how to use 2D:2D matching, see 2D:2D Matching (API Reference).

Important Note: Match Levels 0 to 6 are the only responses returned for 2D:2D Matching.

For 2D:2D Matching, there is a higher possibility of poor image data being used by developers. It is recommended that developers use 3D:2D Matching whenever possible, as this generates a high-quality image from a User's 3D FaceScan to compare with a 2D image (such as an ID or a document).

To learn more about 3D:2D matching, see the Photo ID Matching Guide.

 

Match Levels

FaceTec Match Levels & associated probabilities at <0.99% FRR:

  • Match Level 6 - 1/100,000 FAR

  • Match Level 5 - 1/10,000 FAR

  • Match Level 4 - 1/1,000 FAR

  • Match Level 3 - 1/500 FAR

  • Match Level 2 - 1/250 FAR

  • Match Level 1 - 1/100 FAR

  • Match Level 0 - Non-match


2D Face Image Matching & Liveness Options

2D Face Images from Photo IDs, Govt. Databases, or Social Media Profiles can be matched using FaceTec's SDKs to other 2D images or to 3D FaceMaps, and can be checked for 2D Liveness by FaceTec's Free 2D Single-frame Liveness Detection at PAD Level 1-3 at +98% Accuracy.


2D Face Image Requirements

Your existing 2D Face Images can be used with FaceTec. However, the following set of requirements and recommendations for using 2D images must be adhered to. Your matching accuracy will vary depending on how far your image database deviates from the following requirements and recommendations:

  • JPEG or PNG. No other image formats are accepted.
  • Face has a frontal pose, mugshot style. Variations in pitch, roll, and yaw will lead to poor accuracy.
  • Face should be generally centered in the image. This is not a requirement, but helpful for performance.
  • Face width should be at least 150 pixels wide. Smaller faces are sometimes accepted but will degrade accuracy.
  • Images containing glare, watermarking, or holograms can negatively affect accuracy. The FaceTec Server V8 contains vastly improved accuracy for photos from government issued Photo IDs, when comparing them to FaceTec 3D FaceMaps.
  • Face images should upright. FaceTec SDKs will detect 90, 180, and 270 degree rotated faces in images, but processing will be faster if the photo is upright.

2D Image Recommendations

In general, conformance to ISO 19794-5 Frontal Face specifications will yield better performance. These include the following guidelines:

  • Neutral expression.
  • Good, even, ambient lighting.
  • Evenly lit face, minimizing any shadows and potential glare or reflections in glasses.
  • High resolution image. A good baseline is around 640x360 portrait.

2D Image Low Quality Indicators

Rejection: The FaceTec Server will reject images that are low quality. The logic to determine quality is based on internal, proprietary logic. The reason FaceTec rejects images that are low quality is because FaceTec is relied upon as a security product, and thus, not all images with a face in it can be accepted. When good quality images are used, you will get good quality results.

Low Quality Flag: For images that are borderline quality, the FaceTec Server will allow processing but will flag the 2D FaceMap generated from this image with a "Low Quality Flag". This flag can be used to indicate to the developer that FaceTec has assessed that Matching performance may be degraded on this FaceMap due to the quality of the underlying image.


Security & Use Cases

FaceTec believes the best way to stop Identity Theft is to ask a Potential Fraudster or Bad Actor to put their face on camera and to prove their Liveness. Performing the 3D Liveness Check before a 2D Image Scan is the best defense against Stolen Images or IDs being used. Abiding by an alternative strategy may expose Your System to Real Threats that can otherwise be dispelled with an initial 3D Liveness Check.

In addition to performing a 3D Liveness Check, FaceTec provides several FREE 3D:2D Matching APIs to optimize Security & Usability in Your IDV & KYC System. As the 2D:2D Matching API is only intended for low-security scenarios and controlled environments, FaceTec recommends the 3D:2D Matching APIs for cases where only a single 2D Image is being used for matching.

FaceTec's 3D:2D Matching APIs:

  • FaceTec's 3D:2D Photo ID Matching - Designed to match a Liveness-Proven 3D FaceMap against a 2D Document or ID

  • FaceTec's 3D:2D Face Portrait/NFC Matching for Verifying Legal Identity - Designed to match a Liveness-Proven 3D FaceMap against a 1st Generation digital face image, such as one stored in an NFC chip or a Government Database

  • FaceTec's 3D:2D 3rd-Party ID Photo Image - Designed to match a Liveness-Proven 3D FaceMap against a ID Photo Scan from a Third Party Source. This includes images captured by your own ID Photo Capturing System.

  • FaceTec's 3D:2D Profile Pic - Designed to match a Liveness-Proven 3D FaceMap against a Social Media or Dating App Style Image. This API is useful for assessing the authenticity of Users by comparing them to their Profile Pictures.

  • FaceTec's 3D:2D Kiosk POS - Designed to match a Liveness-Proven 3D FaceMap against a Kiosk or POS Style Image. This API is useful for anyone creating their own front-end capture mechanism for a Kiosk/POS system.

To further optimize Security & Usability, FaceTec's FREE 3D:2D Matching APIs also include several advanced features and tools.

FaceTec's Advanced Features & Tools: