Class 10 AI Unit 5: Computer Vision
10 theory hours · 20 practical hours · 4 theory marks
What this unit is about
Computer vision lets a machine understand images. The unit covers CV tasks, image basics (pixels, resolution, pixel values 0 to 255, grayscale vs RGB), the convolution operator and kernels, and the layers of a convolutional neural network. Practicals use Teachable Machine and Orange.
Learn it with the AI tutor, one minute each
What the unit covers
- What computer vision is, and its applications.
- CV tasks; pixels, resolution and pixel values; grayscale and RGB images.
- The convolution operator and image features.
- CNN: kernels and the layers of a CNN. Practicals with Teachable Machine and Orange.
Key terms
- Pixel
- The smallest dot of an image. In an 8-bit image its value runs from 0 (black) to 255 (white).
- Resolution
- The number of pixels, written width × height, such as 1920 × 1080.
- RGB image
- Each pixel has three values: red, green and blue.
- Kernel
- A small grid of numbers slid over an image to pick out a feature, such as an edge.
- Pooling
- A CNN layer that shrinks the image while keeping the strongest features.
Exam-style questions
1. How is a grayscale image stored differently from an RGB image?
Show answer →
A grayscale pixel has one value (0-255); an RGB pixel has three, one each for red, green and blue.
2. Name the layers of a CNN.
Show answer →
Convolution layer, ReLU (rectified linear unit) layer, pooling layer and fully connected layer.
3. What is the difference between classification and object detection?
Show answer →
Classification says what the image shows; object detection also finds where each object is, drawing a box around it.
Sources
Unit names, hours and marks checked against the official CBSE 2026-27 curriculum on 1 November 2026. Explanations and questions are written by CogniGuru.