Skip to main content
Contact

AI glossary Models & Architecture

What is computer vision?

← All glossary terms
In short

The field of AI that lets machines interpret images and video: recognise objects, read text, detect defects or follow movement.

Explained

Computer vision is the branch of AI that enables machines to extract meaning from images and video. Models trained on large sets of labelled images learn to classify what they see, locate and count objects, segment regions, read text and track movement over time. Deep learning, and convolutional networks and vision transformers in particular, made these tasks reliable enough for production. Common uses include quality control, document reading, medical imaging, retail analytics and safety monitoring.

Main tasks

  • Image classification: what is in this picture?
  • Object detection: where is each object, and how many are there?
  • Segmentation: which pixels belong to which object or region?
  • Optical character recognition (OCR) and document understanding.
  • Tracking and activity recognition in video.
  • Visual question answering with multimodal models that combine images and language.

How businesses use it

  • Manufacturing: detecting defects on a production line.
  • Insurance and claims: assessing damage from photos.
  • Logistics: reading labels, counting stock, checking loads.
  • Healthcare: supporting the reading of scans, with a clinician deciding.
  • Back office: extracting data from scanned forms, invoices and IDs.
  • Retail: shelf monitoring and footfall analysis.

What to watch

  • Data: models need images that look like the real conditions (lighting, angles, cameras).
  • Edge cases: rare defects are the ones that matter and the ones with fewest examples.
  • Privacy: facial recognition and images of people raise GDPR issues, and some uses are restricted or banned under the EU AI Act.
  • Where it runs: on a camera or local device for speed, or in the cloud for heavier models.

Frequently asked questions

What is computer vision in simple terms?

It is teaching computers to understand what is in an image or a video, in a way similar to how people look at a scene. A computer vision system can say what objects are there, where they are and what is happening.

What is the difference between computer vision and image processing?

Image processing transforms images: it adjusts contrast, removes noise or resizes them. Computer vision interprets them to extract information or make decisions. Image processing is often a preparation step for computer vision.

Is computer vision part of AI?

Yes. Modern computer vision relies on machine learning, especially deep learning, to learn visual patterns from examples instead of relying on hand-written rules.

What is an example of computer vision?

Reading the number plate of a car at a car park barrier, spotting a scratch on a part in a factory, or extracting the fields of a scanned invoice. Each one takes an image as input and produces a decision or structured data.

Is facial recognition allowed under the EU AI Act?

The EU AI Act bans some uses, such as untargeted scraping of facial images to build recognition databases, and tightly restricts real-time remote biometric identification in public spaces. Other biometric uses are classed as high-risk and carry obligations. Each case needs a legal review.

How to put it to work

Where it shows up at Thinkia

The Mesh

Further reading

Sources

Updated: 2026-10-21

Want to see how this applies to your organisation?

Talk to an AI Expert