ocr-document-processor

Turn scans, receipts, and cards into structured text.

document processing

What it does

Extracts text and structured data from scanned documents, images, receipts, and business cards.

When to use it

Use for OCR, searchable PDF export, structured extraction, table extraction, receipt parsing, or business-card parsing.

Give it scanned documents or images; it returns OCR or structured exports as files on the computer.

What you provide

No additional actions listed in the analysis.

Python 3 is required to run the bundled scanners.

Requires Pillow 10.0.0 or later.

Requires PyMuPDF 1.23.0 or later.

Requires numpy 1.24.0 or later.