Document Intelligence
Turn any BFSI document into structured, validated data — extracting the right fields from identity proofs, bank statements and more, in seconds.
Overview
What the Document OCR API does
FinHub's OCR API reads identity documents, financial records, invoices, utility bills and cheques, and returns clean structured fields ready for your systems. It's template-agnostic — handling varied layouts and real-world photos — and adds structural validation and tamper detection so a forged or edited document is flagged rather than cleanly transcribed. Sensitive fields can be masked on extraction, sealed to an audit trail.
Inputs
- Document image or PDF
- Document type (optional; auto-detected)
Returns
- Structured fields (name, DOB, number, address…)
- Document classification
- Confidence scores
- Tamper / authenticity signals
POST /v1/documents/ocr
How it works
Three steps to a verified result
Upload the document
Send a photo or PDF — an identity proof, bank statement, payslip, invoice or cheque.
We extract and validate
FinHub classifies the document, extracts the fields, and runs structural and tamper checks.
Get structured data
Receive clean fields with confidence and authenticity signals — with sensitive data masked as needed.
Use cases
Where teams use Document OCR
- Instant KYC and identity capture at onboarding
- Reading bank statements and payslips for underwriting
- Auto-classifying and routing uploaded documents
- Detecting forged or manipulated documents
FAQ
Document OCR API — FAQs
Common questions about FinHub's Document OCR API.
Identity documents (PAN, Aadhaar, passport, driving licence), financial records (bank statements, payslips, ITR), plus invoices, utility bills and cheques — across varied layouts and real-world photos.
More verification APIs
Explore related APIs
Ready to add Document OCR to your flow?
Book a demo and see the API return a verified result on your own test data in minutes.