Emver
Emver
Profiden+ Blog
Documents & Biometrics

ID Document OCR API

Upload a photo or scan of an Indian ID document and receive its fields as structured data: name, number, date of birth, address and document type. Auto-fill forms, cut manual entry and feed the extracted number straight into source verification.

Response
Real-time
Inputs
1 required · 1 optional
Consent
Not required
Billing
Per successful call
POST /v1/id-document-ocr
Sandbox · Production
  1. Your application sends

    • Document image (front, and back where applicable)*
    • Expected document type
  2. Profiden API

    Validates the request, queries the source, normalises the answer and logs the call. Billed only on success.

  3. Verified with

    Profiden document intelligence

  4. You receive

    • Detected document type
    • Extracted fields (name, number, DOB, address)
    • Image quality score
    • Masked identifiers
id-document-ocr Full reference

What the ID Document OCR API does

Manual data entry from ID cards is slow and error-prone. The ID Document OCR API classifies the document, reads its fields and returns them in a clean structure, together with a quality score so blurry or cropped uploads can be rejected up front.

It is designed to sit in front of the verification APIs: extract the PAN or Aadhaar from the image, then validate it at source with a second call on the same key.

Benefits of the ID Document OCR API

Extract structured data from Aadhaar, PAN, passport, DL, voter ID and more.

No manual entry

Forms fill themselves from the document image.

Quality gate

Reject unreadable uploads before they reach a reviewer.

Feeds verification

Extracted numbers flow into source checks with one more call.

Broad document coverage

Aadhaar, PAN, passport, driving licence, voter ID and more.

Use cases

ID Document OCR API use cases

Where the ID Document OCR API is typically called, and what it settles there.

Candidate and customer onboarding

Auto-fill personal details from an uploaded ID.

Mobile-first KYC

Capture and read documents on the phone camera.

Back-office digitisation

Extract data from archives of scanned documents.

Fraud triage

Flag documents whose printed data does not match declared data.

How the ID Document OCR API works

Request and response details, environments and a ready-to-import collection are in the developer console at console.profiden.com.

01

Authenticate

Call with your organisation API key. Sandbox and production use the same contract.

02

Send the inputs

Document image (front, and back where applicable) as a JSON body. Optional fields sharpen the match.

03

We verify at source

Profiden queries the authoritative record, normalises the answer and logs the request.

04

Act on the result

A verification status plus the fields listed above, in the same response envelope as every other API.

Built for the DPDP Act 2023

Consent recorded · Payloads not retained beyond your retention window · Every request traceable

Encryption in transit and at rest
Data processed in India
Per-request audit trail
Masked identifiers in responses

ID Document OCR API: frequently asked questions

What teams ask before adding the ID Document OCR API to their integration.

OCR reads it. Genuineness comes from the source-verification APIs, which Profiden recommends calling with the extracted number.

Images are processed and then purged under your organisation's retention setting. Masked identifiers are returned.

Related APIs

APIs that usually run alongside the ID Document OCR API, on the same key.

All APIs

Get access to the ID Document OCR API

Tell us your use case and expected volume. We set up the organisation, share per-call pricing and issue keys.