Skip to content

Introduction

Face biometrics is a state-of-the-art technology allowing to validate a person identity by means of his face. VERIDAS solution, das-Face, captures the unique features and characteristics of a face, generating a face biometric vector describing uniquely the person.

The facial biometric vector is a mathematical descriptor obtained from the features found in a an recording a person face. The conversion from face into a biometric vector is technically irreversible. Therefore, it is not possible to recover a person’s face from the resulting biometric vector

The solution developed by VERIDAS and implemented in das-Face product is a service-oriented architecture that can be consumed via APIs.

Veridas facial biometric technology submission to the NIST (National Institute of Standards and Technology, USA) ongoing FRVT 1:1 verification 2021 ranking on top 25% worldwide in the category WILD, on the evaluation published on 28th October, 2021. VERIDAS achieved a False Negative Rate of 2.84% for a False Positive Rate of 0.01%, being VERIDAS system 0.14 points from the top-3. "Results shown from NIST do not constitute an endorsement of any particular system, product, service, or company by NIST."

das-Face computes the similarity between faces recorded in images among other operations. The main operations implemented in this product are:

  • Verification: This operation compares two faces to say if both are similar or not, so they can be considered from the same person.
  • Liveness: This operation computes how likely a given capture contains a real face, or it is the result of a spoof attempt.
  • Credential generation: This operations returns a biometric vector computed for the face repre- sented in an image and returns it encoded and ciphered into a proprietary biometric credential format.

Veridas active liveness detection implemented in Selfie-Alive Pro was tested by iBeta to the ISO 30107-3 Biometric Presentation Attack Detection Standard and was found to be in compliance with Level 1.

Beside to previous operations, das-Face supports operations over collections, i.e., galleries, of faces via the integration of das-Face API with the VERIDAS product called das-FaceBond. The operations offered by means of das-FaceBond are:

  • Identification: das-Face offers its API to das-FaceBond for implementation one-face searches versus a collection of N faces, i.e., identification or 1:N search.
  • Clustering: das-Face offers its API to das-FaceBond for clustering of collections of faces, i.e., making groups of faces with high similarity, helping to find duplicates in databases.

das-Face is offered as a REST API. The most common process to obtain the similarity between two faces is:

  1. Two images are sent to the API.
  2. Both images are pre-processed, detecting the faces location in both images, and normalizing the detected faces in the way required for the next process.
  3. The normalized face image is converted into an irreversible mathematical descriptor (facial biometric vector).
  4. Both vectors are compared and a matching score between 0 and 1 is provided. The matching score represents a metric of the similarity between both face images. The higher the score, the greater the certainty to be the same person.
  5. You can use this matching score to validate the identity of a customer. It is recommended to define a threshold within required confidence level using the FPR (False Positive Rate) and FNR (False Negative Rate) expected ratios. The calibration curves are shown at the document Face Biometry Performance Report.

VERIDAS does not store any personal data during the operation of this product. All the user information is immediately deleted.