Modalities
Computer Vision
AI that can interpret images and video — recognising objects, reading text, detecting faces, or describing scenes.
01 ——
In plain English
Computer vision is the branch of AI focused on understanding visual information. It's how AI tools recognise faces, detect objects in self-driving cars, read documents, diagnose medical images, and analyse satellite imagery.
Common tasks:
- Image classification — what's in this picture?
- Object detection — where are the objects, and what are they?
- Optical character recognition (OCR) — extract text from images
- Image segmentation — outline each object precisely
- Image generation — create new images from text descriptions
Modern computer vision mostly uses deep neural networks (CNNs and vision transformers). Multi-modal LLMs like GPT-4o and Claude can also "see" — you can paste an image and ask about it.
Computer vision powers many of the AI tools in this directory's image, video, and design categories.
02 ——
Related terms
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.
Multi-modal
An AI model that can understand and work with multiple types of input — text, images, audio, or video — not just text.
OCR
Optical Character Recognition — AI that converts text inside images, scanned documents, or PDFs into editable, searchable text.
Text-to-Image
AI that generates new images from a written description — the technology behind tools like Midjourney, DALL-E, and Stable Diffusion.
Back to glossaryLast reviewed May 2026