Modalities
OCR
Optical Character Recognition — AI that converts text inside images, scanned documents, or PDFs into editable, searchable text.
01 ——
In plain English
OCR (Optical Character Recognition) is the technology that reads text from images and turns it into actual characters a computer can search, copy, or edit. It's how scanned PDFs, photos of receipts, and screenshots become useful data.
Common uses:
- Document digitisation — scan books, contracts, archives
- Invoice and receipt processing — extract amounts, dates, vendors
- ID and form capture — fill forms automatically from a photo
- Accessibility — read images aloud for visually impaired users
- Translation — translate signs or menus from a phone photo
Modern OCR: Traditional OCR used hand-crafted character templates. Modern OCR uses deep learning and works on messy, multilingual, hand-written, or low-quality images. Multi-modal LLMs like GPT-4o and Claude can also read images directly — often replacing dedicated OCR tools for complex documents.
02 ——
Related terms
Computer Vision
AI that can interpret images and video — recognising objects, reading text, detecting faces, or describing scenes.
Multi-modal
An AI model that can understand and work with multiple types of input — text, images, audio, or video — not just text.
Deep Learning
A type of machine learning that uses layered neural networks to learn complex patterns — the foundation of modern AI.
Neural Network
A computing system inspired by the brain, made up of layers of connected "neurons" that learn patterns from data — the building block of modern AI.
Back to glossaryLast reviewed May 2026