Identity document data extraction

ID Card & Passport Data Extraction

Extract structured data from ID cards and passports without manual copy-paste. Upload identity documents, capture the fields you need, and export the result to XLS, CSV or JSON.

77 languages OCR Custom fields XLS · CSV · JSON 1 credit per page
ID Card / Passport extraction
Passport / IDOCR Ready
P<UTOERIKSSON<<ANNA<MARIA<<<<<<<<
L898902C36UTO7408122F1204159ZE184226B<<<<<10
Full nameAnna Maria Eriksson
Document numberL898902C3
Date of birth1974-08-12
NationalityUTO
Expiry date2012-04-15
XLS CSV JSON

Why it matters

Turn identity documents into usable data

ID cards and passports contain critical information for onboarding, verification and administrative workflows. Heyyel Data Extractor helps you capture that information in a structured format, reducing the repetitive work involved in manual data entry.

⚡

Reduce manual entry

Stop retyping names, document numbers, dates and nationality details into forms, spreadsheets or internal systems.

🔍

Extract the fields that matter

Capture core identity fields or use custom data extraction when your process requires fields beyond the standard identity document setup.

🧩

Use structured output

Export extracted identity data to XLS, CSV or JSON so it can be reviewed, shared or used in downstream workflows.

Common extracted fields

Capture key data from ID cards and passports

Start with the document type preset and keep the suggested fields, or add your own extraction rules when you need more control. You can see the full configuration flow on the How It Works page.

Full name

Extract the document holder’s full name.

Document number

Capture the passport or ID number.

Date of birth

Identify the holder’s birth date.

Nationality

Extract citizenship or nationality details.

Issue date

Find the date the document was issued.

Expiry date

Capture the expiration date.

Sex / Gender

Extract the stated sex or gender when present.

MRZ data

Read machine-readable zone information from passports and compatible IDs.

Address or place of birth

Capture additional identity details when they appear on the document.

How it works

From identity document to structured output

The workflow follows the same logic as Heyyel Data Extractor, with a document type preset that helps you start faster.

01

Upload your file

Upload an ID card or passport in PDF, PNG, JPG, WebP or TIFF format.

02

Choose ID Card / Passport

Select the identity document type to start with suggested extraction fields.

03

Configure fields and language

Edit labels, keys, field types and required settings. Add extraction hints and use auto-detect or choose the document language manually.

04

Run extraction

Heyyel Data Extractor processes the document, using OCR when needed, and identifies the values that match your requested fields. If you want the distinction in more detail, see OCR vs data extraction.

05

Review the results

Check the extracted fields alongside the document preview before exporting or using the data.

06

Export your data

Download the output in XLS, CSV or JSON depending on how you want to use it next.

OCR + extraction

More than OCR alone

OCR answers: “What text is inside this document?”
Heyyel Data Extractor answers: “Which identity data do I actually need?” Learn more about the broader process in our guide to how AI document data extraction works.

Scanned documents Image-based IDs Structured fields Custom extraction hints Review before export

Use cases

Useful for identity-driven workflows

✅

KYC onboarding

Extract core identity fields to support customer onboarding and verification tasks.

🗂️

Administrative processing

Move identity information into structured records more easily.

🏨

Travel & hospitality

Capture passport or ID details for guest, traveler or visitor workflows.

📊

Back-office operations

Reduce manual data entry and create cleaner records for downstream teams.

Identity documents are often processed alongside other business records. The same Heyyel Data Extractor workflow can also be used for invoice data extraction, receipt data extraction, contract data extraction and bank statement data extraction.

Formats and output

Built for common document inputs and structured exports

📁

Supported uploads

Process PDF, PNG, JPG, WebP and TIFF identity documents. For a broader PDF workflow, see how to extract specific data from PDF documents.

🌍

77 languages

Work with multilingual document collections, with auto-detect or manual language selection.

📤

Export options

Use the extracted data in XLS, CSV or JSON format.

FAQ

ID card and passport extraction, explained

Heyyel Data Extractor can extract fields such as full name, document number, date of birth, nationality, issue date, expiry date, sex or gender, MRZ data, and other fields you define.

Yes. Start from the ID Card / Passport document type and then edit, remove, or add fields with custom labels, keys, data types, required settings and extraction hints.

Yes. OCR is used when needed to read scanned or image-based identity documents before the data is returned in a structured format.

Supported file formats include PDF, PNG, JPG, WebP and TIFF.

Extracted identity data can be exported to XLS, CSV or JSON.

Heyyel Data Extractor uses a simple page-based model: one processed page uses one credit.

Try it on your documents

Extract the identity data you need — without retyping it

Use Heyyel Data Extractor to turn ID cards and passports into structured data that is easier to review, export and use in your workflow.

Identity documents Custom fields OCR XLS · CSV · JSON 1 credit per page