What does Veridexa do?

Veridexa is an enterprise AI platform that verifies documents and detects fraud in identities, invoices, and KYC files using forensic analysis, OCR, and machine learning.

How does Veridexa protect data?

Documents are processed with encryption in transit and at rest on secure cloud infrastructure, with regional data residency options in EU, US, and APAC.

Banks, insurers, fintechs, and marketplaces use Veridexa to automate KYC, catch document forgery, and reduce manual review.

Face Verification

ArcFace (MobileFaceNet) 1:1 face matching with encrypted templates.

Live Engine

Run Face Verification View API Documentation

Engine

src/lib/verification/biometric-core/face-recognition (ONNX Runtime Web)

API

POST /api/public/biometrics/v1/enroll · /compare

Face Verification is a full 1:1 engine. BlazeFace detects a single face, 5-point landmarks drive a similarity transform for aligned ArcFace inference, and 512-dim embeddings are L2-validated before compare. Templates are stored AES-256-GCM encrypted with versioned key rotation.

What is implemented

BlazeFace ONNX detector + heuristic fallback
ArcFace MobileFaceNet embeddings (512-d)
Quality gate: brightness, sharpness, pose, face count
Encrypted storage in face_recognition_templates
Cosine similarity + decision threshold
Runtime capability detection: WebGPU → WASM SIMD → WASM baseline

Modules

src/lib/verification/biometric-core/face-recognition/
  arcface-embedder.ts
  detector.ts
  engine.ts
  embedding-validation.ts
  crypto.server.ts
  identify.ts
  liveness.ts

Biometric APIs SDK Back to overview