ID Tech

Facial Recognition

Facial recognition matches a photo of a face to an identity.

Facial recognition is a biometric modality that analyses the geometry and texture of a person’s face to establish identity. Modern systems rely on CNN embeddings and achieve <0.1% FNMR on NIST FRVT benchmarks.

Latest Updates

  • 2025-07-01: Tinder, Deliveroo, Uber Eats and Just Eat expanded selfie or facial-verification checks to fight bots, deepfakes and illegal-account rentals in CA and UK gig-economy platforms.

References

Vendors using Facial Recognition

Aware, Inc.Cognitec SystemsCLEAR Secure, Inc.Daon, Inc.FaceTecHID GlobalIDEMIAJumioNEC CorporationNeurotechnologyOnfidoShufti ProSuprema Inc.Thales GroupVeriffLakota Software SolutionsAuthenticIDKeylessInnovatrics

Latest Data Cards

  • Data Card

    Aware announces third-party testing results across PAD, bias testing, DHS RIVR, and passkey readiness

    2026-02-17CC-BY-4.0padpasskeys-webauthnfacial-recognitionaware

    Aware released external validation results across ISO/IEC 30107-3 Level 2 presentation attack detection, ISO/IEC 19795-10 bias testing, DHS Rapid Identity Verification Rally participation, and FIDO2 passkey readiness.

    • Aware achieved ISO/IEC 30107-3 Level 2 PAD certification, covering advanced presentation attack scenarios.
    • The company also demonstrated ISO/IEC 19795-10 bias testing compliance and FIDO2 passkey readiness.
    • DHS RIVR participation builds on Aware's top performance in prior DHS security testing announced in June 2025.
  • Data Card

    Onondaga County advances biometric surveillance signage bill after Wegmans controversy

    2026-02-17CC-BY-4.0facial-recognitionvoice-recognition

    Onondaga County, New York advanced legislation requiring businesses to display visible notices before any area where biometric data—including facial recognition, fingerprint scanning, and voice recognition—is collected, following Wegmans' adoption of biometric disclosure signage and broader retail scrutiny in New York and Connecticut.

    • The bill covers surveillance, access control, and customer tracking uses of biometric identifiers in commercial settings.
    • Enforcement mechanisms include monetary penalties for non-compliance; the bill advanced through committee in mid-February 2026.
    • Wegmans posted biometric disclosure signage at New York City locations in January 2026, prompting the county's legislative action.
  • Data Card

    Wicket expands Major League Soccer agreement to deploy facial authentication across 2026 events

    2026-02-16CC-BY-4.0facial-recognition

    Wicket expanded its Major League Soccer agreement to deploy facial authentication as an identity layer for event operations across multiple 2026 league events, including Generation Adidas Cup, MLS NEXT Flex, and MLS NEXT Cup, as well as existing MLS club programs at LAFC, Columbus Crew, and Atlanta United.

    • Wicket's facial authentication is designed to speed up check-in and reduce manual verification at stadium and event venues.
    • The deployment extends to MLS NEXT developmental competitions and multiple league events throughout 2026.
    • Earlier 2025 Wicket deployments supported MLS NEXT competitions and the All-Star Game in Austin.
See more data cards

Frequently Asked Questions

How does facial recognition work?
Facial recognition uses algorithms to analyze facial features—such as the distance between eyes or the shape of cheekbones—to create a unique digital signature for identification.
How accurate is facial recognition technology?
Modern facial recognition systems can achieve very low false match rates (below 0.1%) under controlled conditions, but accuracy may vary with lighting, pose, and image quality.
What are common concerns around facial recognition?
Concerns include privacy violations, potential bias against certain demographic groups, and misuse by surveillance systems without consent.
What is Presentation Attack Detection (PAD)?
PAD aims to detect spoofing attempts (e.g., photos, masks, deepfakes) and is evaluated separately from matching accuracy using standards-driven tests.
What are 1:1 vs 1:N operations?
1:1 verifies a claimed identity (authentication), while 1:N searches across a gallery (identification). They have different accuracy and scalability considerations.