OCR & Computer Vision | Vlens

The OCR API (/v1/ocr/) is a standalone computer vision service for document extraction, face matching, liveness detection, and compliance checks. It operates independently from the Digital Identity flow — you can use it without user registration.

National ID

Front and back extraction as separate calls

Passport

MRZ and biographical data extraction

Car License

Owner info (front) and vehicle specs (back), plus V2 combined model

Driving License

Egyptian driving license data extraction

Face Recognition

Face match (vs. ID photo), face compare, and liveness detection

General & Others

Auto-detect any document via /general, or submit unknowns via /others

License Plate

Egyptian vehicle plate text extraction

Commercial Registry

CR document data extraction

Transliteration

Arabic text to English transliteration

Base URL and authentication

The OCR API uses a different base path from the Digital Identity API:

https://api.vlenseg.com/v1/ocr/

Every request requires:

1 ApiKey: YOUR_TENANT_API_KEY
2 Authorization: Bearer YOUR_ACCESS_TOKEN
3 Content-Type: application/json

Common request format

All OCR endpoints accept a JSON body with image as a base64-encoded string, plus optional transaction and control fields:

1 {
2   "image": "BASE64_ENCODED_IMAGE",
3   "transaction_id": "optional-uuid-to-group-steps",
4   "client_transaction_id": "your-own-reference",
5   "country": "EGY",
6   "getExtractedData": true
7 }

Field	Required	Description
`image`	Yes	Base64-encoded JPEG or PNG. Max 3 MB.
`transaction_id`	No	Group multiple steps into one transaction. Omit to start a new one.
`client_transaction_id`	No	Your own reference ID.
`country`	No	Defaults to `EGY`.
`getExtractedData`	No	Include full extracted fields in the response. Default `false`.

Common response format

1 {
2   "services": {
3     "validations": { "validation_errors": [] },
4     "spoofing": { "fake": false },
5     "classification": { "doc_type": "national_id" },
6     "liveness": null,
7     "AML": null,
8     "SRC": null
9   },
10   "data": { ... },
11   "error_code": null,
12   "error_message": null
13 }

data contains document-specific extracted fields. All step outputs include transaction_id, request_id, and client_transaction_id.

Save transaction_id from any step to chain subsequent calls or to look up the record later via the admin Transactions API.

Lookup transaction by ID (admin)

Retrieve the full record for any OCR or Digital Identity transaction. Pass the transaction_id returned by any OCR step (e.g. id/front, passport, liveness) or Digital Identity verify call (verify/id/front, verify/id/back, verify/liveness/multi).

Requires ApiKey and an admin bearer token.

cURL

JavaScript

Python

$ curl "https://api.vlenseg.com/api/Transactions/GetTransactionById?id=TRANSACTION_ID" \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer ADMIN_TOKEN"

If the ID is invalid or expired, the API returns error code 5004 (Transaction Not Found). See Error codes.

National ID

Scan front

$ curl -X POST https://api.vlenseg.com/v1/ocr/id/front \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "image": "BASE64_ID_FRONT",
>     "getExtractedData": true
>   }'

Response data fields:

Field	Description
`name`	Full Arabic name
`firstName` / `lastName`	Arabic name components
`nameEnglish`	Transliterated full name
`firstNameEnglish` / `lastNamesEnglish`	Transliterated name components
`idNumber`	National ID number
`idKey`	ID key
`dateOfBirth`	Date of birth
`gender`	Gender
`govern` / `governEnglish`	Governorate
`address` / `addressEnglish`	Full address
`address1` / `address2`	Address line components
`city` / `district`	City and district
`transaction_id`	Use in subsequent steps

Scan back

$ curl -X POST https://api.vlenseg.com/v1/ocr/id/back \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "image": "BASE64_ID_BACK",
>     "transaction_id": "TX_FROM_FRONT"
>   }'

Response data fields: maritalStatus, job, jobTitle, religion, husbandName, releaseDate, idExpiry, idNumber, gender

Passport

$ curl -X POST https://api.vlenseg.com/v1/ocr/passport \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "image": "BASE64_PASSPORT_IMAGE"
>   }'

Response data fields:

Field	Description
`passport_no`	Passport number
`name`	Full name
`nationality`	Nationality
`country_code`	Issuing country ISO code
`gender`	Gender
`Date_of_Birth`	Date of birth
`Date_of_Expiry`	Expiry date
`doc_Type`	Document type (e.g. `P` for passport)

Car license

License front (owner information)

$ curl -X POST https://api.vlenseg.com/v1/ocr/car/license/front \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{"image": "BASE64_LICENSE_FRONT"}'

Response data fields: license_number, license_type, name, nationality, address, expiry, issuance, traffic_unit

License back (vehicle information)

$ curl -X POST https://api.vlenseg.com/v1/ocr/car/license/back \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{"image": "BASE64_LICENSE_BACK"}'

Response data fields: model_year, type, sub_type, chasis, volume, motor, color, fuel, cylinder, examination_dt

Driving license

$ curl -X POST https://api.vlenseg.com/v1/ocr/driving_license \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{"image": "BASE64_DRIVING_LICENSE"}'

Response data fields: nameArabic, nameEnglish, nationalID, nationalityArabic, nationalityEnglish, licenseType, job, address, expiryDate, issuanceDate, trafficUnit1, trafficUnit2

Face recognition

Face match (face vs. ID photo)

Match a face image against the ID front photo stored in a transaction. Requires completing the id/front step first for the same transaction_id.

$ curl -X POST https://api.vlenseg.com/v1/ocr/face/match \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "image": "BASE64_FACE_IMAGE",
>     "transaction_id": "TX_WITH_ID_FRONT"
>   }'

Response data fields:

Field	Description
`isMatched`	Whether the face matches the ID photo
`dissimilarity`	Distance score (lower = more similar)
`threshold`	Match threshold used (default `2.4`)
`score`	Match confidence score
`detected_face_image`	Whether a face was detected in the submitted image
`detected_id_face_image`	Whether a face was detected in the ID photo

Face compare (two faces)

Compare any two face images directly, without requiring an ID transaction.

$ curl -X POST https://api.vlenseg.com/v1/ocr/face/compare \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "face_image1": "BASE64_FACE_1",
>     "face_image2": "BASE64_FACE_2",
>     "liveness": "2"
>   }'

Response data fields: same as Face Match — isMatched, dissimilarity, threshold, score

Liveness detection

Verify that a face image is from a live person, using three frames captured in quick succession.

$ curl -X POST https://api.vlenseg.com/v1/ocr/liveness/multi \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "face_1": "BASE64_FACE_1",
>     "face_2": "BASE64_FACE_2",
>     "face_3": "BASE64_FACE_3",
>     "transaction_id": "TX_WITH_ID_FRONT"
>   }'

All three images must be of the same person and captured within 0.5 seconds of each other. Compress each to under 500 KB.

License plate recognition

$ curl -X POST https://api.vlenseg.com/v1/ocr/license_plate \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{"image": "BASE64_CAR_IMAGE"}'

Response data fields: result — the extracted plate text

Document classification

Identify the type of document in an image before processing it with a specific endpoint.

$ curl -X POST https://api.vlenseg.com/v1/ocr/classification \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{"image": "BASE64_DOCUMENT"}'

Response services.classification.doc_type returns the detected type (e.g., national_id, passport, driving_license).

Liveness multi (standalone)

Run liveness detection using three face frames, without being tied to a Digital Identity user account. Same as /v1/ocr/liveness/multi.

$ curl -X POST https://api.vlenseg.com/v1/ocr/multi \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "face_1": "BASE64_FACE_1",
>     "face_2": "BASE64_FACE_2",
>     "face_3": "BASE64_FACE_3",
>     "transaction_id": "YOUR_UUID"
>   }'

All three face images must be of the same person and captured within 0.5 seconds of each other. Compress each to under 500 KB.

Response services.liveness returns true if the face images are live.

General document scan

Auto-detects the document type and extracts all available fields without specifying an endpoint upfront. Useful when the document type is unknown at call time.

$ curl -X POST https://api.vlenseg.com/v1/ocr/general \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "image": "BASE64_DOCUMENT",
>     "getExtractedData": true
>   }'

Response services.classification.doc_type indicates the detected type. data contains the extracted fields for that document type.

Car license V2

An updated model for car license scanning with improved accuracy. Accepts a single image and extracts both owner and vehicle data.

$ curl -X POST https://api.vlenseg.com/v1/ocr/car/licenseV2 \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{"image": "BASE64_CAR_LICENSE"}'

Commercial registry (CR)

Extract data from an Egyptian commercial registry document.

$ curl -X POST https://api.vlenseg.com/v1/ocr/cr \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{"image": "BASE64_CR_DOCUMENT"}'

Transliteration

Convert Arabic text to its English transliteration.

$ curl -X POST https://api.vlenseg.com/v1/ocr/transliteration \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{"image": "BASE64_DOCUMENT"}'

AML validation

Check a name or ID number against criminal and AML records.

$ curl -X POST https://api.vlenseg.com/v1/ocr/aml/validate \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "idNumber": "29901234567890",
>     "name": "Ahmed Mohamed"
>   }'

File upload variants

Every endpoint has an equivalent /file variant that accepts multipart/form-data instead of base64. Replace the endpoint path with /file suffix and send the image as a form field:

$ curl -X POST https://api.vlenseg.com/v1/ocr/passport/file \
>   -H "ApiKey: YOUR_API_KEY" \
>   -H "Authorization: Bearer TOKEN" \
>   -F "file=@passport.jpg"

Available /file variants: id/front/file, id/back/file, car/license/front/file, car/license/back/file, car/licenseV2/file, passport/file, face/match/file, driving_license/file, license_plate/file, classification/file, others/file

OCR vs. Digital Identity verify

	OCR API (`/v1/ocr/`)	Digital Identity (`/api/DigitalIdentity/verify/`)
Requires user registration	No	Yes
Links result to a user account	No	Yes
Sets `isDigitalIdentityVerified`	No	Yes
Suitable for standalone extraction	Yes	No
Includes NTRA / CSO authority checks	No	Yes (configurable)

Use the OCR API when you need raw document extraction or biometric checks without tying the result to a Vlens user. Use the Digital Identity verify flow when you need the result to count toward a user’s verification status.

Base URL and authentication

Common request format

Common response format

Lookup transaction by ID (admin)

cURL

JavaScript

Python

National ID

Scan front

Scan back

Passport

Car license

License front (owner information)

License back (vehicle information)

Driving license

Face recognition

Face match (face vs. ID photo)

Face compare (two faces)

Liveness detection

License plate recognition

Document classification

Liveness multi (standalone)

General document scan

Car license V2

Commercial registry (CR)

Transliteration

Other documents

AML validation

File upload variants

OCR vs. Digital Identity verify