Computer vision basics in Intro to Computing - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is computer vision?

Computer vision is a field of computer science that teaches computers to see, understand, and interpret images and videos like humans do.

beginner

Name three common tasks in computer vision.

Common tasks include image classification (telling what is in an image), object detection (finding objects and their locations), and image segmentation (dividing an image into meaningful parts).

beginner

What is an image represented as in computer vision?

An image is represented as a grid of pixels, where each pixel has color values, often in red, green, and blue (RGB) channels.

intermediate

Why do we use convolutional neural networks (CNNs) in computer vision?

CNNs are used because they can automatically find important patterns like edges and shapes in images, helping the computer understand visual data better.

beginner

What is the difference between image classification and object detection?

Image classification tells what is in the whole image (like 'cat' or 'dog'), while object detection finds where each object is in the image and labels them.

What does a pixel in an image represent?

A A small dot with color information

B A sound wave

C A text character

D A network connection

A pixel is the smallest unit in an image and holds color information.

Which task involves finding the location of objects in an image?

A Image classification

B Data cleaning

C Object detection

D Image enhancement

Object detection finds and locates objects within an image.

What type of neural network is most commonly used for image tasks?

A Convolutional Neural Network (CNN)

B Recurrent Neural Network (RNN)

C Feedforward Neural Network

D Transformer Network

CNNs are designed to process images by detecting patterns like edges and shapes.

What does image segmentation do?

A Converts images to text

B Divides an image into meaningful parts

C Compresses image size

D Removes noise from images

Image segmentation splits an image into parts that represent different objects or regions.

Which color channels are commonly used to represent images?

A Black, White, Gray

B Yellow, Cyan, Magenta

C Alpha, Beta, Gamma

D Red, Green, Blue

Images are usually represented using RGB color channels.

Explain in your own words what computer vision is and why it is useful.

Think about how computers can 'see' and help us with pictures or videos.

Describe the difference between image classification and object detection with simple examples.

Imagine telling what is in a photo versus pointing out where things are.