Invoice OCR - Data Recognition from Photos, Scans, and PDFs

Take a photo of a receipt, scan an invoice, or use a digital PDF - the tool reads them all. It uses optical character recognition (OCR) to extract amounts, dates, and vendor names, then matches everything to your bank transactions automatically.

How It Works

Drop a bank statement PDF and your invoices into the app. The tool extracts text from each file using PDF.js for digital PDFs and Tesseract OCR for scanned images. It identifies amounts, dates, vendor names, and currency from the extracted text.

Then it runs a matching algorithm that compares each receipt against your bank transactions by amount, date, and vendor name. High-confidence matches are applied automatically; lower-confidence ones are suggested for your review.

Supported Formats

Upload PDF invoices, JPG photos, or PNG scans. The tool handles European number formats (comma as decimal separator, space as thousands separator) and recognizes amounts in EUR, USD, GBP, CZK, and other currencies. Bank statements from Revolut, SLSP, and Tatra banka are parsed automatically.

Private and Free

All OCR and matching runs locally on your machine. No external AI models are involved, so your personal data stays private. No account required, completely free. Learn more about our local processing approach.