Computer Vision

You looked at your phone and it unlocked. Nothing magical happened — a camera turned your face into a few hundred thousand coloured dots, and a model decided those dots were you.

1What the domain is

Computer Vision (CV)

Computer Vision is the domain of AI that gives a machine the ability to get and analyse visual information and then predict a decision about it. The process is acquiring, screening, analysing, identifying and extracting information from an image.

Its main objective

The main objective of this domain is to teach machines to collect information from pixels. CV projects translate digital visual data into descriptions, which are then turned into computer-readable language to help make a decision.

Three domains, three kinds of data

Pick a domain and it rises. What is standing on the pedestal is the data that domain is fed. Drag sideways to turn.

Computer Vision is fed images and video.

Takes in visual information — photographs, video, camera and sensor images — analyses it, and makes a decision about what it sees. Its aim is to collect information from pixels.

Examples: Face unlock on a phone · Crop and pest monitoring by drone · Surveillance systems, self-driving cars

2What can be fed in

Not only photographs. The input to a CV machine can be photographs, videos, and pictures from thermal or infrared sensors, indicators, and other sources — anything that arrives as an image.

A wall of tiny coloured tiles

Stand close to a mosaic and you see only tiles. Step back and you see a face. A machine never gets to step back — it only ever has the tiles. Computer Vision is teaching it to work out the face from the tiles alone.

3Examples CBSE uses

Agricultural monitoring

Drones with cameras photograph farmland from the air. The images are analysed for crop health, pests and likely yield, so farming can be planned better.

Surveillance systems

Cameras watching public spaces, buildings and borders can detect suspicious activity, track a person or a vehicle, and alert security staff in real time.

Also in this domain: face unlock, self-driving cars reading the road, reading a number plate at a toll gate, and a doctor’s X-ray being checked by a model.

4From the board papers

A self-driving car fails to detect pedestrians crossing at night, resulting in a near accident. Which domain of AI technology should be enhanced to improve safety?
(a) Natural Language Processing (b) Statistical Data (c) Recommendation Systems (d) Computer VisionCBSE sample paper 2025–26

1 mark

▶Show the answer

(d) Computer Vision. The failure is in seeing — the car did not recognise a person in a camera image. That is exactly what the CV domain does.

What is the main goal of Computer Vision projects?
(A) Translating audio data into visual descriptions (B) Converting digital data into analogue signals (C) Teaching machines to understand textual information (D) Converting digital visual data into computer-readable languageCBSE AI Class X textbook, Unit 1

1 mark

▶Show the answer

(D). CV turns visual data into descriptions a computer can act on. Understanding text is NLP, not CV.

5Check yourself

Quick Check

A drone photographs a field and a model reports which parts have pests. Which domain?

Quick Check

The main objective of Computer Vision is to teach machines to collect information from:

← Previous

🔢 Statistical Data

Natural Language Processing 💬