What Is Computer Vision? Real-World Examples

1About This Guide

Your phone unlocks with your face, sorts photos by who's in them, and reads text from a picture. That's

computer vision. This guide explains how machines learn to "see" — without the maths. By the end you'll

2What Is Computer Vision?

Computer vision is the field of AI that teaches machines to interpret images and video — to identify

objects, read text, recognise faces, and understand scenes. It's how software turns raw pixels into

3How Computers 'See' an Image

To a computer, an image isn't a picture — it's a grid of numbers. Each pixel is a value (or three, for

colour). A vision model works entirely with these numbers, learning which patterns of pixels correspond to

4How Vision Models Learn

Vision models learn from huge collections of labelled images. Shown thousands of cats labelled "cat", a

model gradually learns the patterns that make a cat a cat. Modern systems use neural networks that

5Task 1: Image Classification

The simplest task: given an image, say what it is — "this is a dog", "this scan looks normal". The model

6Task 2: Object Detection

A step further: find where objects are, drawing boxes around each and labelling them. This is what lets a

7Task 3: Segmentation

More precise still: label every pixel, outlining exactly which pixels belong to which object. It's used in

medical imaging and photo-editing tools that separate a subject from its background.

• Phones: face unlock, photo search, scanning documents.
• Medicine: helping spot issues in scans and x-rays.
• Vehicles: reading the road for driver assistance and self-driving.
• Retail: automated checkout and shelf monitoring.
• Learn Python and the basics of machine learning first.