UNIT 5 COMPUTER VISION

WORKSHEET
A. Tick (✔) the correct option.
Exercise Solved Questions
SECTION A (Objective Type Questions)
1. In which of the following images, the shades range starts with 0 and ends with
255?
a. Grayscale images c. Black and white images
b. RGB images d. High resolution images
2. Which among the following images around us are made up of 3 primary colors of
Red, Green and Blue?
a. Moving c. Monochrome
b. Static d. Colored
3. What does OpenCV stands for?
a. Open Computer Vision c. Open Compilation Version
b. Open-Source Computer Vision d. Open Computer Version
4. Which of the following is commonly used in applications such as image retrieval
and automated vehicle parking systems?
a. Instance Segmentation c. Localization
b. Object detection d. Classification
5. Which of the following is the most popular architecture used for image
classification?
a. Neural Networks c. Data Sciences
b. Computer Vision d. Convolutional Neural Networks (CNNs)
6. Which of the following is not an application of CV?
a. Face filters c. Chatbots
b. Damage analysis d. Self driving cars
7. Which of the following is an example of image classification in CV?
a. Price prediction c. Trend setting
b. Photo albums in smartphones d. Facelock in smartphone
8. What are neural networks?
a A series of Hidden Layers c. Fully connected
b. Made up of artificial neurons d. All of the above

B. Fill in the blanks.

1. Computer vision works on the same phenomena as that of
2. ___________ means where the object is in the image.
3. ____________ is the process of identifying or detecting the instances of real-world
objects.
4. ___________ means giving multiple images as input to the Computer Vision
application.
5. A_______________algorithm takes an image as input and outputs a collection of
regions (or segments).
6. Colour of a pixel is determined by the number of______it represents.
7. _________ is basically the dimensions through which you can measure how many
pixels are on a screen.
8. Pixel stands for___________
9. ___________is calculated by displaying the numbers of Pixels displayed
vertically or with the number of Pixels displayed horizontally.
10. The most common pixel format is _____________
11. A_________image is the one in which the value of each pixel is single.
12. All the colors are made by mixing the 3 basic colors of the RGB in
varying___________
13. In ____________ an image feature is simply a piece of information about the
content of an image.
14._____________ helps in processing images and videos to identify objects, faces,
or even handwriting.
15. A __________image has each pixel of size 1 byte having a single plane of 2D
array of pixels.
C. State whether the following statements are true or false.

1. Computer Vision means giving eyes to the computer.

2. It is not necessary to import cv2 for OpenCV.
3. Giving the path of the image is optional if the file is in the current working directory.
4. By default, OpenCV represents the images in BGR.
5. In OpenCV we cannot convert BGR to RGB.
6. We need to download the get-pip.py file if not installed in the system.
7. Every coloured image has 3 channels- RGB.
8. In a grayscale image the value of each pixel is single.
9. Pixel stands for "Pixilate Element".
D. Match the following:
1. Object detection a. CNN
2. Image Classification b. Computer Vision
3. Retail business c. Amazon Go
4. Pixel d. Static image
5. Resolution e. Megapixels

A. Short answer type questions:

SECTION B (Subjective Type Questions)
1. Differentiate between Max pooling and Average Pooling.
Ans. There are two types of pooling:
Max Pooling: Max Pooling is the most commonly used method that selects the
maximum value of the current image view and helps preserve the maximum
detected features.
Average Pooling: Average Pooling finds out the average value of the current image
view and thus down samples the feature map.
2. Name the four important layers in CNN.
Ans. The 4 layers in CNN are:
● Convolutional Layer
● Rectified linear Unit (ReLU)
● Pooling Layer
● Fully Connected Layer
3. Name the real-life applications of Computer Vision.
Ans. The real-life application of Computer Vision are:
• Facial Recognition in Smartphones
• Face Filters Google Translate apps
4. How does the computer see an image?
Ans. In a digital image, every colored image that is stored can be split into 3 different
channels, i.e., Red (R), Green (G) and Blue (B), with different intensities. The
computer identifies the value related to each pixel and determines the size and color
of the image.
B. Long answer type questions:
1. What are the uses of feature maps?
Ans. Feature maps have multiple uses like: • • The output of the filter applied to the
previous layer is trapped by the feature map. It helps in reducing the size of the
image so that it can be processed easily. It helps in focusing on the important
features of the images like eyes, nose etc. so that it can be processed efficiently.
2 Define Computer Vision? Which industry has got its maximum usage?
Ans. It is a domain of Artificial Intelligence that enables computers to see, observe
and understand digital images or data, process them by acquiring, screening,
analysing, identifying and extracting information using the machine learning and
neural network algorithms. It is ruling the industries like manufacturing, automobiles,
power plants etc.
3. Explain three important applications of Computer Vision?
Ars. Three important applications of Computer Vision are:
● Image classification and object detection: Google's search by images is an
example of Computer Vision. The input image compares different features
with the image database and once it matches, gives us the search result.
● Banking: Nowadays, to deposit a cheque you don't have to go to bank. Click a
picture of the cheque from your phone of both the sides of the cheque.
● Agriculture: Computer Vision is used in agriculture in various ways. With the
use of object detection, a fruit on a tree can give an estimate on your yield. As
a farmer you can predict how much you are going to get.
4. Explain the task used in computer vision applications for single object.
Ans. The two-task used in Computer Vision application does for single object are:
Classification: It is the process of finding out the class/category of the input image.
The input image is processed using a machine learning algorithm and classified into
predefined categories.
• Classification + Localisation: Localisation means where the object is in the image.
So, this combined task of classification and localisation means processing the input
image to identify its category along with the location of the object in the image.
5. What do you mean by Grayscale image?
Ans. A grayscale image is the one in which the value of each pixel is single, i.e., it
carries only intensity information. Also known as Black and White, it has shades of
grey. RGB channels of pixels have the same value. These are images with only 2
colors, Black and White, varying from Black at the weakest intensity to white at the
strongest. A grayscale image has each pixel of size 1 byte having a single plane of
2D array of pixels. In grayscale images, the shades range starts with 0 and ends with
255, i.e., it starts with pure black and ends with pure white.
6. Explain the parameters of the imread() in OpenCV.
Ans. This function read the image and loads it into the computer's memory:
cv2.imread (path, flag)
path: is the path of the image to be read. If the file is in the working directory, then
write only the name and the extension of the image otherwise it is a must to specify
the complete path.
flag: how our image should be read.
The value can be:
1-(default) It reads image in BGR format where it has bluish appearance.
0-It reads image in Grayscale format.
-1-It reads image in original format.

Key
Answers
Exercise (Section A)
A. 1. a
2. d
3. b
4. b
5. d
6. c
7. b
8. d

B. 1. Human vision
2. localisation
3. object detection
4. multiple objects
5. segmentation
6. bits
7. resolution
8. picture element
9. screen resolution
10. byte image
11. grayscale
12. intensity
13. computer vision
14. OpenCV
15. grayscale
C. 1. True 2. False 3. True 4. True
5. False 6. True 7. True 8. True 9. False
D. 1. c 2. a. 3. d 4. b 5. e

A. Tick() the correct option.

Unsolved Questions
SECTION A (Objective Type Questions)
1. Which of the following is an open-source software library for computer vision and
machine learning that helps a computer understand the content of digital images?
a. Object detection b. Segmentation
c. OpenCV d. Localisation
2. A ______algorithm takes an image as input and outputs a collection of regions (or
segments).
a. segmentation b. localisation
c. OpenCV d. Computer Vision
3. Which of the following are not the tasks that CV helps in agriculture?
a. Yield predict b. Spraying of pesticides
c. Weeding d. Control the rainfall
4. Which of the following reads the image and loads it into the computer's memory in
OpenCV?
a loadimage() c image()
b. imread() d. readimage()

B. Fill in the blanks.

1.___________ means giving the ability to the computer to see the world just like
humans.
2. Computers can make. _______. about images without any human assistance.
3.________ the process of finding out the class/category of the input image.
4._________ is the process of division of an image into smaller objects so that the
machine can identify an object from the background.
5.________ is the smallest unit of information in a digital image.
6 ________ features help to identify the images and for analysis purposes.
7. Google's search by images is an example of______________.
8. __________ function is used for converting from BGR to RGB.
9. Expand ROI ____________
10. __________ function is used to increase or decrease the size of the image in the
given frame.
11._____________ are a series of algorithms used to recognise hidden patterns in
raw data, cluster and classify it, and continuously learn and improve.
12. A Neural Network is divided into multiple layers and each layer is further divided
into several blocks called ______________

C. State whether these statements are true or false.

1. The process layer of Neural Networks predicts our final output.
2. Image Feature is a piece of information about the content of the image.
3. Colour of a pixel is determined by the number of colors it represents.
4. Cropping means reducing the size of the image.
5. Augmented Reality is an example of real-life application of CV.
6. Neural Networks are a series of algorithms used to recognise hidden patterns in
raw data.

D. Match the following:

1. Image classification a. Digital images
2. Single objects b. Shades of grey
3. Pixel c. One object
4. OpenCV d. Computer Vision
5. Gray scale images e. Smallest unit

A. Short answer type questions:

SECTION B (Subjective Type Questions)
1. Write three differences between Computer Vision and Human Vision.
2. What is a Pixel? Give any two important features of a Pixel in a digital image.
3. What do you mean by the term-Image Features?
4. What is OpenCV Computer Vision Library?
5. Can we save an altered image using OpenCV in our drive? Give a code to do so.
B. Long answer type questions:
1. Explain the task used in computer vision applications for multiple objects.

Key
UNSOLVED QUESTIONS -
Exercise (Section A)
A. 1. c
2. a
3. d
4. b

B. 1. Computer vision
2. inferences
3. classification
4. instance segmentation
5. pixel
6. image
7. computer vision
8. cv2.COLOR_BGR2RGB
9. Region of interest
10. resize()
11. neural networks
12. nodes

C. 1. False 2. True 3. False 4. False 5. True

6. True
D. 1. d 2. c. 3. e 4. a 5. b

III. Short answer questions:

1. Write three differences between computer vision and human vision?
Computer Vision Human Vision
Computer vision allows a computer Humans pursue things as they are And
to sense its surroundings and identify retain what they recognize storing gate
things similar to how human vision deep in the brain until they come
perceives things. across those things again.
It uses machine learning techniques It is about how eyes detect light
and algorithms to identify distinguish patterns and coordinate with the brain
and classify objects to translate light into images
Object detection is one of the most Humans recognize objects effortlessly
challenging problems in computer and have no problems describing
vision objects in a science
 2.What is a pixel? Give any two important features of a pixel in a digital
image.
A pixel is the smallest unit of a digital image or display, and it has two
important features.
Color: Each pixel has a specific color value that determines its appearance in
color imaging systems, a color is typically represented by three component
intensities, such as red, green and blue.
Resolution: The number of pixels in an image determines its resolution. More
pixels results in sharper and more detailed visuals.

3.What do you mean by the term Image Features?

An image feature is a descriptive parameter that is extracted from an image or
video to interpret visual content. Image features can be edges objects or points.

4. What is OpenCV computer vision library?

Open CV is an open source computer vision library that provides programming
functions for real-time computer vision . It can be used to build applications
across cross-platform and operating systems.

5.Can we save an altered image using open cv in our drive? Give a code
to do so.
Yes, we can save an altered image Using OpenCV in our drive. OpenCV
imwrite() function is used to save an image to a Specified file.
The code to save the image according to the specified format in current
working directory.
Syntax: cv2. imwrite(filename, image) Parameters: filename: A string
representing the file name.

V. Long answer questions

1. Explain the task used in computer vision applications for multiple
objects.
The computer vision applications are based on a certain number of task
performed on an input image to get the desired output which can be used to do
predictions or analysis of data.
Single objects
This means giving one image as input to the computer vision application it can
be further divided into 2 categories.
Classification:
classification is the process of finding out the class or category of the input
image.
Classification + localization:
localization means where the object is in the image. So, this combined task of
classification and localization means processing the input image to identify its
category along with the location of the object in the image.
Multiple objects this means giving multiple images as input to the computer
vision application. It can be further divided into two categories:
object detection:
object detection is the process of identifying or detecting the instances of real
world objects like cars bicycles buses animals or anything on which the
detection model has been trained.
Instant segmentation:
Instant segmentation is the process of division of an image into smaller objects
so that the machine can identify an object from the background or by using
information about other objects present along with it in the input image.