Computer vision is the part of AI that lets machines understand images and video, from recognising objects to reading text and tracking movement.
In plain words
A digital image is just a grid of numbers. Computer vision models learn from many labelled examples to turn those numbers into meaning: what is in the picture, where it is, and what shape it has. Core tasks include classifying a whole image, detecting objects with boxes, and segmenting their exact outlines. Many harder tasks build on these.
A quick example
A doctor's software looks at a chest X-ray and highlights areas that may show pneumonia. The model has learned from many labelled scans which patterns matter, and flags them for the radiologist to review.
Where you'll meet it
- Face unlock on phones and reading text from scanned documents.
- Medical imaging, self-driving cars and factory inspection.
Related
Sources
- DocsWhat is computer vision?, IBM Think · read 29 Sept 2026
- DocsImage Classification, Stanford CS231n · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 29 Sept 2026. Spotted an error? Report it.