---
title: "OCR (optical character recognition)"
description: "OCR, optical character recognition, converts images of text, such as scans and photos, into machine-readable characters. It answers 'what letters are on this pa"
canonical: https://automataai.hu/en/glossary/ocr
language: en
publisher: Automata AI
updated: 2026-09-19
---

# What is OCR (optical character recognition)?

OCR, optical character recognition, converts images of text, such as scans and photos, into machine-readable characters. It answers 'what letters are on this page', not 'what does this invoice mean'. Intelligent document processing builds on OCR by adding the understanding layer.

## Why OCR alone is not enough

OCR gives you a wall of text with no idea which number is the total and which is the invoice number. Extraction, validation and routing are separate steps, and that is where the manual work used to be.

## FAQ

**Does OCR handle Hungarian accents correctly?**

Current engines do, including ő and ű, on reasonable-quality scans. Handwriting remains the weak spot.

Related: https://automataai.hu/en/glossary/intelligent-document-processing