CBSE | DEPARTMENT OF SKILL EDUCATION

ARTIFICIAL INTELLIGENCE
QUESTION BANK – CLASS 10
CHAPTER – 5 CMPUTER VISION

Fill in the Blanks.

1. Visuals search uses CV to help users search for different objects using real-world
images.
2. Facial recognition powered by CV is used to verify the identity of visitors and guests
in smart homes.
3. The Google Translate app is a free tool that can do real-time visual translations of up
to 88 languages with the help of CV.
4. Computers see images as a collection of Pixels.
5. The number of pixels in an image is called resolution.
6. In a grayscale image, each pixel is stored as one byte, forming a simple plane of a 2D
array of pixels.
7. When the value of all three primary colours is the same, the image form is a
grayscale image.
8. Features of an image are details that tell us what is in the image.
9. In image processing, convolution is performed by sliding a kernel over different
portions of the picture
10. The ReLU layer in the CNN gets rid of all the negative numbers in the feature map
11. The pooling layer in a CNN is responsible for reducing the spatial size of the
convolved feature
12. Open CV is an open source computer vision and image processing library
13. Each channel consist a number of pixels with the value of each pixel, ranging from 0
to 255.
14. A bounding box is a rectangular frame drawn by the algorithm around the object,
indicating its spatial location within the image.
15. A coloured image is made up of pixels that have three different values, i.e., red, blue
and green.

Write T for True and F for False.

1. OpenCV can be used To process images and videos to identify objects, faces or even
handwriting.T
2. In image processing features like corners are difficult to locate F
3. The first correlation layer in a CNN is responsible for extracting high level features.F
4. When we change the pixel values of an image, the image changes T
5. In a byte image, the pixel value is stored as an 8 bit integer with a range of values
from 0 to 200F
6. In a field of Agriculture, CV can process image data captured by drone cameras to
help in remotely monitoring crops.T
7. Google translate is capable of identifying and translating text that is part of an
image.T
8. In an angle, the smaller pixel values closer to zero represent lighter shades, while the
larger number closer to 255 represent darker shades. T
9. In an image processing for each position of the kernel, the corresponding pixel values
are multiplied and added together to replace the original centre pixel.T
10. In a grayscale image, the darkest shade is represented by a pixel value of 255 F

Select the Correct Option.

1. The objective of computer vision is _______________

a) To replace human vision
b) To understand human language
c) To plot graphs
d) To solve mathematical equations
2. Identify the use of computer vision in the retail business
a) Count footfalls
b) Autonomous checkouts
c) Detect suspicious activity
d) All of these
3. What is the smallest unit of information that makes up a text image or video on a
computer?
a) Pixel
b) Element
c) Dot
d) Unit
4. What is the term used to describe the number of pixels in an image?
a) Pixel size
b) Image quality
c) Resolution
d) Dimension
5. In computer vision what task are associated with single object in an image?
a) Image classification
b) Image classification plus localization
c) Object detection
d) Instance segmentation
6. What is the purpose of convolutional image processing?
a) To extract features from images
b) To resize the images
c) To apply filters directly on the image
d) To rotate the images
7. Which of the following CNN layers is responsible for classifying the image into a
label?
a) Convolution
b) Fully connected layer
c) Pooling
d) ReLU
8. What does the imshow() function do in open CV?
a) It displays images on the screen
b) It saves images as files
c) It applies filters to images
d) It converts images to grayscale
9. What is the purpose of the imread() function in openCV?
a) To read and load images from files
b) To display images on the screen
c) To apply filters to images
d) To resize images
10. Which of the following is true for feature maps in the context of CNNs?
a) They help extract and highlight important features
b) They reduce the size of the image
c) They allow us to focus on important features
d) All of these
11. Image convolution is a process that is used _______________.
a) Apply different effects to an image
b) Increase the size of an image
c) Crop an image
d) Copy an image
12. Where is the result of convolutions stored?
a) Output mask
b) Feature detector
c) Output matrix
d) Pixel array
13. Convolution performs the _________Operation on to arrays
a) Division
b) Multiplication
c) Subtraction
d) Exponential
14. When a coloured image is split, we get_________ of pixels
a) 0 channel
b) One channel
 c) Three channels
d) 4 channels
15. Which of the following is the task of instance segmentation?
a) Identify an object within an image
b) Finding out the location of the object
c) Labelling individual instances of objects
d) Identify the object category

1. What is Computer Vision? Explain with example.

Computer vision is a field of computer science and artificial intelligence that focuses on
enabling computers and systems to interpret and understand visual information from the
world, such as images and videos. The goal of computer vision is to develop algorithms and
models that allow machines to process visual data in a way that mimics human vision,
enabling them to recognize, analyze, and make decisions based on visual input.

Key components of computer vision include:

1. Image Processing: Techniques used to enhance or manipulate images to make them

suitable for analysis.
2. Feature Extraction: Identifying and extracting important attributes or characteristics
from images.
3. Object Detection: Identifying and locating objects within images or videos.
4. Image Classification: Categorizing images into predefined classes or labels.
5. Image Segmentation: Dividing an image into meaningful regions or segments for
more detailed analysis.
6. Pattern Recognition: Identifying patterns and regularities in visual data.

Computer vision combines methods from various fields, including machine learning,
statistics, and computer science, to enable machines to understand and interact with the visual
world. Applications of computer vision are vast and include areas such as autonomous
vehicles, facial recognition, medical imaging, and industrial inspection.

2. Write any five applications of Computer Vision.

Facial Recognition:
 Application: Used for security and identification purposes, such as unlocking
smartphones, verifying identities in security systems, or tagging people in social
media photos.
 Example: Facial recognition systems in airports for passenger identification and
border control.
Autonomous Vehicles:
 Application: Enables self-driving cars to interpret and navigate their surroundings by
recognizing objects, road signs, lane markings, pedestrians, and other vehicles.
 Example: Tesla's Autopilot system uses computer vision to assist with lane-keeping,
adaptive cruise control, and automatic emergency braking.
Medical Imaging:
  Application: Assists in analyzing medical images (such as X-rays, MRIs, and CT
scans) to diagnose diseases, detect abnormalities, and plan treatments.
 Example: AI algorithms for detecting tumors or fractures in medical images,
improving diagnostic accuracy and efficiency.
Retail and Inventory Management:
 Application: Automates tasks such as checking stock levels, managing inventory, and
enhancing the shopping experience through features like checkout-free stores.
 Example: Amazon Go stores use computer vision to track items that customers pick
up and automatically charge them upon exit.
Agriculture and Farming:
 Application: Used for monitoring crops, detecting diseases or pests, and optimizing
harvests through image analysis of fields and plants.
 Example: Drones equipped with computer vision systems to assess crop health and
guide precision farming techniques.

3. Explain following tasks used in computer vision with the help of

example.
Classification
Classification + Localisation
Object Detection
Instance Segmentation

The various applications of Computer Vision are based on a certain number of tasks
which are performed to get certain information from the input image which can be
directly used for prediction or forms the base for further analysis. The tasks used in a
computer vision application are:

Classification Image Classification problem is the task of assigning an input image

one label from a fixed set of categories. This is one of the core problems in CV that,
despite its simplicity, has a large variety of practical applications.
 Classification + Localisation This is the task which involves both processes of
identifying what object is present in the image and at the same time identifying at
what location that object is present in that image. It is used only for single objects.

Object Detection Object detection is the process of finding instances of real-world

objects such as faces, bicycles, and buildings in images or videos. Object detection
algorithms typically use extracted features and learning algorithms to recognize
instances of an object category. It is commonly used in applications such as image
retrieval and automated vehicle parking systems.

Instance Segmentation Instance Segmentation is the process of detecting instances

of the objects, giving them a category and then giving each pixel a label on the basis
of that. A segmentation algorithm takes an image as input and outputs a collection of
regions (or segments).

4. Explain grayscale image and list its applications.

Grayscale and RGB images are two fundamental types of image representations used
in computer vision and image processing, each with distinct characteristics and
applications.

Grayscale Images

Definition:
 Grayscale images contain shades of gray, ranging from black to white, without any
color information.
 Each pixel in a grayscale image represents intensity, with values typically ranging
from 0 (black) to 255 (white) in an 8-bit image.

Characteristics:
 Single Channel: Grayscale images have only one channel representing intensity.
 Reduced Complexity: They contain less data compared to RGB images because they
only represent intensity, not color.
Applications:

1. Medical Imaging: Often used in X-rays, MRI, and CT scans where color information
is less important than detail and contrast.
2. Document Scanning: Useful for scanning and processing text documents, where
color is not necessary.
3. Image Compression: Often used in scenarios where storage space is limited and
color information is not crucial.
4. Edge Detection: Techniques like Sobel or Canny edge detection are commonly
applied to grayscale images to identify features and boundaries.
5. Computer Vision Algorithms: Many vision algorithms, such as those for pattern
recognition and object detection, use grayscale images for simplicity and speed.

5. Explain RGB image and its applications.

RGB Images

Definition:
 RGB (Red, Green, Blue) images contain color information by combining three color
channels: red, green, and blue.
 Each pixel in an RGB image has three values, corresponding to the intensity of red,
green, and blue, which combine to produce a wide spectrum of colors.

Characteristics:
 Three Channels: RGB images have three channels, one for each color component.
 Color Information: They represent the full color spectrum, allowing for detailed and
accurate color reproduction.

Applications:
1. Photography: Standard for digital cameras and smartphones to capture and display
vibrant, full-color images.
2. Video: Used in video recording and streaming for rich visual content.
3. Computer Graphics: Essential for rendering graphics in gaming, virtual reality, and
graphical user interfaces (GUIs).
4. Image Editing: Tools like Adobe Photoshop use RGB images for detailed color
manipulation and enhancement.
5. Color-based Object Detection: Applications that rely on distinguishing objects
based on color, such as in autonomous vehicles or augmented reality.

6. Differentiate between Human Vision and Computer Vision.

As humans, we visually perceive the world around us not just in static images but
with a combination of colors, textures, motion, depth, and context. On the other
hand, computer vision typically focuses on specific visual features without
considering anything else.
7. What is meant by image features and what is their use in CV?
In computer vision and image processing, a feature is a piece of information which is
relevant for solving the computational task related to a certain application. Features
may be specific structures in the image such as points, edges or objects.
For example: Imagine that your security camera is capturing an image. At the top of
the image we are given six small patches of images. Our task is to find the exact
location of those image patches in the image. Take a pencil and mark the exact
location of those patches in the image.
 8. What is the difference between Pixel and Resolution? Which of these
defines the quality of the image?

Pixel

 Definition: A pixel, short for "picture element," is the smallest unit of a digital image
or display. It represents a single point in a raster image or display screen.
 Characteristics: Each pixel has its own color and brightness value. In a color display,
a pixel is often composed of sub-pixels with different colors (usually red, green, and
blue) that combine to create a full range of colors.
 Role: Pixels are the building blocks of digital images. The more pixels an image or
screen has, the finer the detail it can display.

Resolution

 Definition: Resolution refers to the total number of pixels in an image or display,

typically expressed as a width by height measurement. It indicates the amount of
detail an image or display can show.

Characteristics: Higher resolution means more pixels, which generally leads to a

clearer and sharper image. Common resolutions include 1920x1080 (Full HD),
2560x1440 (Quad HD), and 3840x2160 (4K Ultra HD).

 Role: Resolution impacts the quality and clarity of the visual content. For displays, it
determines how sharp and detailed the images and texts appear. For images, it affects
how large you can print or display the image before it starts to look blurry.

Pixel Resolution
The basic unit of digital images and displays The measure of how many pixels make up
the image or display, typically given as width
x height (e.g., 1920x1080)
Resolution typically defines the quality of an image. Higher resolution means more pixels, which
generally leads to greater detail and clarity. However, other factors like pixel density (for displays)
and image processing also influence overall image quality

9. What do you understand by pixel value?

Each of the pixels that represent an image stored inside a computer has a pixel value which
describes how bright that pixel is, and/or what colour it should be. The most common pixel
format is the byte image, where this number is stored as an 8-bit integer giving a range of
possible values from 0 to 255.

Typically, zero is to be taken as no colour or black and 255 is taken to be full colour or white.
Why do we have a value of 255? In the computer systems, computer data is in the form of
ones and zeros, which we call the binary system. Each bit in a computer system can have
either a zero or a one. Since each pixel uses 1 byte of an image, which is equivalent to 8 bits
of data? Since each bit can have two possible values which tells us that the 8 bit can have 255
possibilities of values which starts from 0 and ends at 255.

[Link] a short note on the applications of computer vision in sports.

In sports, computer vision is used for:

 Player Performance Analysis: Tracking and analyzing player movements and stats.
 Tactical Analysis: Evaluating game strategies and opponents.
 Injury Prevention: Monitoring movements to prevent injuries.
 Refereeing: Assisting with decisions and automated calls.
 Fan Engagement: Enhancing broadcasts and AR experiences.
 Training: Providing feedback and improving skills.
 Scouting: Identifying and evaluating talent.
 Broadcast Automation: Automatically tracking action for broadcasts.