Urgent.News

What's breaking now, across thousands of outlets.

Tech

Built-in-SA facial biometrics speeds up authentication and onboarding

SoftiDoc’s facial biometrics authentication and onboarding systems use multiple AI models trained specifically for the African market, says Jeremy Engelbrecht, MD of SoftiDoc.

Built-in-SA facial biometrics speeds up authentication and onboarding

Facial biometrics technology has become increasingly popular for customer authentication and onboarding, making processes faster, more convenient, and less susceptible to identity fraud. This technology, developed locally for Africa's demographics and priced in South African rands, is now a cost-effective solution accessible to small and medium-sized businesses, as reported by Jeremy Engelbrecht, Managing Director of SoftiDoc, a South African SaaS solution provider.

Previously, facial biometrics required specialized cameras and equipment, but advancements in mobile phone technology have made advanced facial biometrics authentication more feasible. According to Engelbrecht, facial biometrics now account for around 55% of the global $35.9 billion face and voice biometrics market. Mobile-based facial biometrics is versatile and cost-effective, eliminating the need for specialized equipment and offering robust and accurate authentication, enabling businesses to secure transactions conveniently for customers.

The process involves sending an SMS with a prompt for customers to take a photo of their ID and a three-second selfie. SoftiDoc's facial biometrics system confirms the ID's legitimacy, matches the person to the ID, and verifies the person's identity through various metrics. These include depth map analysis of the facial image, texture analysis, light reflection tracking, and Fourier transform, which converts image feature data into frequency components to identify spoofing attempts like masks and replay attacks.

SoftiDoc's facial biometrics systems undergo rigorous testing at iBeta Quality Assurance, an accredited third-party testing laboratory that evaluates biometric systems for liveness detection and Presentation Attack Detection (PAD). Trained on millions of clips from older phones and various devices, the AI has been specifically developed for the African market, ensuring high accuracy for darker-toned skins. The pricing model is volume-based, making it accessible to most businesses on a per-transaction basis.

Written by urgent.news from ITWeb's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at itweb.co.za →

More in Tech

Building an Automated QA KPI Dashboard for Playwright & BDD Pipelines

Tracking test automation metrics manually often leads to outdated figures and missed engineering gaps. To solve this, automated reporting directly from your test suites—such as Playwright and…

  • Total test suite: 120 tests (94 automated, 26 manual)
  • Last run (2026-05-29): 94 executed, 87 passed, 7 failed
  • 3 defects opened, 1 closed (average resolution time: 2 days)

More from Wednesday 26 August →