ID Document Verification

Verify government-issued identity documents across 54 African countries. AfriRoute extracts data with AI-powered OCR, validates document authenticity, and optionally matches the document photo against a live selfie in a single API call.

Supported documents include national IDs, passports, driver's licenses, and voter IDs, plus country-specific registries such as Nigeria's BVN, Ethiopia's Fayda, and the Ghana Card.

🚀 Quick Start

curl -X POST https://api.afriroute.ai/api/v1/identity/verify-id \
  -H "Authorization: Bearer $AFRIROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "document_type": "national_id",
    "country": "ET",
    "image_front": "<base64-encoded-image>",
    "image_selfie": "<base64-encoded-selfie>",
    "customer_info": {
      "full_name": "Abebe Kebede",
      "id_number": "ET123456789"
    },
    "callback_url": "https://yourapp.com/identity/callback"
  }'

📡 Endpoints

Verify ID Document

POST /v1/identity/verify-id

Performs OCR extraction, authenticity detection, and — when a selfie is supplied — face matching and liveness in one request.

Parameters

Field	Type	Required	Description
document_type	string	Yes	national_id, passport, drivers_license, or voter_id
country	string	Yes	ISO 3166-1 alpha-2 code (e.g. ET, NG, GH)
image_front	string	Yes	Base64-encoded front image of the document
image_back	string	No	Base64-encoded back image (required for some IDs)
image_selfie	string	No	Base64 selfie to enable face match + liveness
customer_info	object	No	Declared data to cross-check against the document
registry_check	string	No	Government registry to validate against: bvn, fayda, ghana_card
callback_url	string	No	Webhook URL for the verification.completed event

Get Verification

GET /v1/identity/verification/:verification_id

Retrieve the full result of a previously submitted verification.

💻 Code Samples

Node.js

const fs = require('fs');

const idFront = fs.readFileSync('national-id-front.jpg', 'base64');
const selfie = fs.readFileSync('customer-selfie.jpg', 'base64');

const res = await fetch('https://api.afriroute.ai/api/v1/identity/verify-id', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer $AFRIROUTE_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    document_type: 'national_id',
    country: 'ET',
    image_front: idFront,
    image_selfie: selfie,
    customer_info: { full_name: 'Abebe Kebede', id_number: 'ET123456789' }
  })
});

const data = await res.json();
console.log(data.status, data.confidence);

Python

import base64, requests

with open('national-id-front.jpg', 'rb') as f:
    id_front = base64.b64encode(f.read()).decode()
with open('customer-selfie.jpg', 'rb') as f:
    selfie = base64.b64encode(f.read()).decode()

res = requests.post(
    'https://api.afriroute.ai/api/v1/identity/verify-id',
    headers={'Authorization': 'Bearer $AFRIROUTE_API_KEY'},
    json={
        'document_type': 'national_id',
        'country': 'ET',
        'image_front': id_front,
        'image_selfie': selfie,
        'customer_info': {'full_name': 'Abebe Kebede', 'id_number': 'ET123456789'}
    }
)
print(res.json()['status'])

📊 Response

{
  "verification_id": "ver_abc123xyz",
  "status": "verified",
  "confidence": 98.2,
  "document": {
    "type": "national_id",
    "country": "ET",
    "number": "ET123456789",
    "full_name": "ABEBE KEBEDE",
    "date_of_birth": "1990-05-15",
    "expiry_date": "2030-01-10",
    "authentic": true,
    "expired": false
  },
  "face_match": { "match": true, "confidence": 97.8 },
  "liveness": { "passed": true, "confidence": 96.5 },
  "risk_assessment": { "risk_level": "low", "risk_score": 3, "flags": [] },
  "verification_time": "2026-05-10T14:30:00Z"
}

Verification Statuses

Status	Meaning
verified	Document authentic and all checks passed
pending	Processing or awaiting manual review
rejected	Failed authenticity, face match, or liveness checks
expired	Document is past its expiry date

💡 Best Practices

• Capture sharp, well-lit images — blur and glare are the top causes of low confidence scores.
• Always send image_back for documents that carry an MRZ or data on the reverse.
• Pass customer_info so AfriRoute can cross-check declared data against extracted fields.
• Handle the webhook, not just the synchronous response, in production — verification can take several seconds.
• Use registry_check for high-assurance KYC (BVN, Fayda, Ghana Card) where government validation is required.

⚠️ Error Handling

Code	HTTP	Description
INVALID_DOCUMENT_TYPE	400	Unsupported document_type for the given country
IMAGE_QUALITY_LOW	422	Image too blurry, dark, or cropped to process
DOCUMENT_EXPIRED	422	Document is past its expiry date
FACE_MISMATCH	422	Selfie does not match the document photo
REGISTRY_UNAVAILABLE	503	Government registry temporarily unreachable

See the error code reference for the full list.

📚 Related Resources

• Document Scanning (OCR)
• Face Matching
• Liveness Detection
• Identity API Reference
• ID Verification Tutorial

---

Last Updated: May 2026 | Need help? [email protected]