RBG colours

• All the coloured images are made up of three primary colours Red, Green and Blue.
• All the other colour are formed by using these primary colours at different
proportions.
• Computer stores RGB Images in three different channels called the R channel, G
channel and the B channel.

Image Features
• A feature is a description of an image.
• Features are the specific structures in the image such as points, edges or objects.
• Other examples of features are related to tasks of CV motion in image sequences, or
to shapes defined in terms of curves or boundaries between different image regions.

Open CV or Open Source Computer Vision Library is that tool that helps a computer
to extract these features from the images. It is capable of processing images and videos
to identify objects, faces, or even handwriting.

Questions on Computer Vision

One Mark Questions
Q.No Question
1. What is the primary goal of Computer Vision?
A) To enhance image quality
B) To interpret and make decisions based on visual data
C) To store images efficiently
D) To increase resolution of images
2. Which of the following is an example of an application of Computer Vision?
A) Word processing
B) Speech recognition
C) Facial recognition
D) Data encryption
3. What does a pixel represent in an image?
A) A segment of a video
B) The smallest unit of an image
C) The color depth of an image
D) The brightness of an image

130
4. Which of the following tasks involves identifying and locating objects within
an image?
A) Image compression
B) Feature extraction
C) Object detection
D) Image enhancement
5. A _______________ is a technology based on computer vision that
identifies, verifies, or matches a digital image of a human face against a
database of stored facial images.
6. What does segmentation in Computer Vision refer to?
A) Enhancing image details
B) Dividing an image into parts or regions
C) Reducing image size
D) Increasing image resolution
7. A grayscale image represents intensity values ranging from 0 to ________.
8. What is feature extraction in Computer Vision?
A) Reducing image noise
B) Identifying and describing relevant characteristics from an image
C) Increasing image contrast
D) Storing image data
9. What is the main function of the Google Translate App when interpreting
foreign language signs?
A) To provide dictionary definitions
B) To teach grammar rules
C) To translate text into your preferred language almost instantly
D) To convert voice to text
10. What does the pixel value represent in a grayscale image?
A) The color
B) The intensity
C) The contrast
D) The brightness
11. Which of the following is a common use of Computer Vision in medical
imaging?
A) Audio transcription
B) Image segmentation
C) Video streaming
D) Data encryption
12. Which of the following is a primary color in the RGB color model?
A) Yellow B) Cyan
C) Green D) Magenta

131
13. What is a common application of Computer Vision in security systems?
A) Document editing
B) Video streaming
C) Facial recognition
D) Web browsing
14. Which format is typically used to store a color image in digital form?
A) Grayscale
B) Binary
C) RGB
D) Indexed
15. ____________ is the core technology behind the development of
autonomous vehicles
16. ____________allows you to point your phone’s camera at the words and tell
you what it means in your preferred language almost instantly.
17. True/False
A higher resolution in an image implies less detail.
Assertion Reasoning Questions
18. Assertion (A): Computer vision is a field of artificial intelligence that enables
computers to interpret and make decisions based on visual data from the world.

Reasoning (R): Computer vision uses algorithms to process and analyse images
and videos, enabling tasks like object detection and facial recognition.

A. Both A and R are true, and R is the correct explanation for A.

B. Both A and R are true, but R is not the correct explanation for A.
C. A is true, but R is false.
D. A is false, but R is true.
E. Both A and R are false.

19. Assertion (A): Image classification is the process of categorizing and labeling
groups of pixels or vectors within an image based on specific rules.
Reasoning (R): Image classification is a crucial step in medical imaging,
allowing for the diagnosis of diseases from X-rays or MRI scans.
A. Both A and R are true, and R is the correct explanation for A.
B. Both A and R are true, but R is not the correct explanation for A.
C. A is true, but R is false.
D. A is false, but R is true.
E. Both A and R are false.

132
20 Assertion (A): Computer vision can be used in automated quality inspection in
manufacturing industries.
Reasoning (R): Automated quality inspection systems use computer vision to
identify defects or irregularities in products on a production line.

A. Both A and R are true, and R is the correct explanation for A.

B. Both A and R are true, but R is not the correct explanation for A.
C. A is true, but R is false.
D. A is false, but R is true.
E. Both A and R are false.

Subjective Questions-2 marks

1. Explain the term "Computer Vision" and its primary goal.
2. What is the significance of Computer Vision in AI?
3. Name two applications of Computer Vision in the healthcare industry.
4. Describe an application of Computer Vision in the automotive industry.
5. What is the role of feature extraction in Computer Vision?
6. Explain the concept of image segmentation.
7. Differentiate between object detection and image classification.
8. What is the significance of edge detection in Computer Vision tasks?
9. Define pixel and explain its importance in digital images
10. What is resolution, and how does it affect image quality?
11. Explain the difference between grayscale and RGB images
12. How is pixel value represented in a grayscale image?
13. Describe the role of color channels in an RGB image.
14. What are the advantages of using high-resolution images in Computer Vision
tasks?
15. Explain how pixel density affects the visual quality of an image.

Subjective Questions-4 marks

1. Explain two different real-world applications of Computer Vision and how they
benefit society.
2. Explain the concepts of pixel value, resolution, and color channels in digital
images, and how they collectively affect image quality.
3. Discuss the evolution of Computer Vision and its impact on modern technology.
4. Describe the concept of feature extraction and its importance in different
Computer Vision tasks.
5. Compare and contrast object detection, image classification, and image
segmentation in Computer Vision.
Case Study/Application-Based Questions on Computer Vision- 5 marks

133
1. Case Study: Autonomous Vehicles

An autonomous vehicle relies on Computer Vision to navigate and make driving

decisions. Explain how Computer Vision helps in tasks such as lane detection,
pedestrian recognition, and traffic sign recognition. Additionally, discuss the
potential challenges that the vehicle might face in adverse weather conditions
and how these can be mitigated
2. Case Study: Medical Imaging

In the healthcare industry, Computer Vision is utilized for analysing medical

images such as MRI and CT scans. Describe how Computer Vision can assist in
detecting abnormalities such as tumours, and discuss the advantages of using this
technology in early diagnosis and treatment planning.
3. Case Study: Surveillance Systems

Consider a smart surveillance system that employs Computer Vision for security
purposes. Explain how object detection and facial recognition are used in this
system to enhance security. What ethical considerations should be considered
when implementing such a system?
4. Case Study: Digital Image Restoration

A company specializes in restoring old, damaged photographs using Computer

Vision techniques. Explain how understanding pixel values, resolution, and color
channels is crucial in this process. How does Computer Vision enhance the
quality of these restored images?
5. Case Study: Retail Industry
In the retail industry, Computer Vision is used to improve customer experience
and store management. Describe how Computer Vision can be applied for tasks
such as inventory management, customer behaviour analysis, and automated
checkout. What are the benefits and challenges associated with implementing
these technologies in retail stores?
Answers

Q.No One Mark Answers

1. B) To interpret and make decisions based on visual data
2. C) Facial recognition
3. B) The smallest unit of an image
4. C) Object detection
5. facial recognition system
6. B) Dividing an image into parts or regions
134
7. 255
8. B) Identifying and describing relevant characteristics from an image
9. C)To translate text into your preferred language almost instantly
10. B) The intensity
11. B) Image segmentation
12. C) Green
13. C) Facial recognition
14. C) RGB
15. Computer vision
16. Google Translate app
17. FALSE
18. Both A and R are true, and R is the correct explanation for A.
19. B) Both A and R are true, but R is not the correct explanation for A
20. Both A and R are true, and R is the correct explanation for A.

Subjective Questions-2 marks

1. Computer Vision is a field of Artificial Intelligence that enables computers to
interpret and make decisions based on visual data, with the primary goal of
automating tasks that the human visual system can do.
2. Computer Vision is significant in AI because it allows machines to understand
and interpret visual information, leading to automation in areas like image
recognition, object detection, and scene understanding, which are crucial for
applications such as autonomous driving and medical imaging.
3. Two applications of Computer Vision in healthcare are medical imaging
analysis (e.g., detecting tumors in MRI scans) and surgical assistance systems
(e.g., guiding robotic surgery with real-time imaging).
4. In the automotive industry, Computer Vision is used in autonomous vehicles for
tasks such as lane detection, pedestrian recognition, and traffic sign recognition,
enhancing safety and enabling self-driving capabilities
5. Feature extraction involves identifying and describing relevant characteristics
from an image, which can then be used for tasks such as object recognition,
classification, and tracking.
6. Image segmentation is the process of dividing an image into multiple regions or
segments, each representing a different part of the image. This helps in isolating
objects and understanding the structure of the scene.
7. Object detection identifies and locates objects within an image, providing
bounding boxes for each object, whereas image classification assigns a label to
the entire image based on the objects it contains without providing their
locations.
8. Edge detection is significant because it helps in identifying the boundaries and
structure within an image, which is essential for object detection, segmentation,
135
 and recognition tasks.

9. A pixel is the smallest unit of a digital image, representing a single point in the
image with a specific color or intensity. Pixels are important because they
collectively form the entire image, determining its resolution and detail.
10. Resolution refers to the number of pixels in an image, usually measured in
pixels per inch (PPI). Higher resolution means more pixels and greater detail,
resulting in better image quality.
11. Grayscale images consist of shades of gray, ranging from black to white, with
each pixel representing an intensity value. RGB images use three color channels
(Red, Green, Blue), where each pixel is a combination of these three colors,
allowing for a wide range of colors in the image.
12. In a grayscale image, the pixel value is represented by an intensity level ranging
from 0 to 255, where 0 represents black, 255 represents white, and values in
between represent different shades of gray.
13. In an RGB image, each pixel has three color channels (Red, Green, Blue). The
intensity of each channel determines the final color of the pixel. By combining
different intensities of these three channels, a wide range of colors can be
represented.
14. High-resolution images provide more detail and clarity, which can improve the
accuracy of Computer Vision tasks such as object detection, recognition, and
segmentation, as they allow for better feature extraction and analysis.

15. Pixel density, measured in pixels per inch (PPI), affects the sharpness and clarity
of an image. Higher pixel density means more pixels are packed into a given
area, resulting in a crisper and more detailed image, which is particularly
important for high-quality displays and prints.

Subjective Questions-4 marks Answers

1. Healthcare: Computer Vision is used in medical imaging to detect anomalies
such as tumours, improving early diagnosis and treatment outcomes. It also
assists in robotic surgeries, providing precise guidance and enhancing surgical
accuracy.

Security: In security systems, Computer Vision is used for facial recognition to

identify individuals in surveillance footage, aiding in crime prevention and
investigation. It enhances public safety by monitoring public spaces and alerting
authorities to suspicious activities.

136
2. Pixel Value: In digital images, pixel value represents the intensity or color
information of a pixel. In grayscale images, it ranges from 0 (black) to 255
(white). In RGB images, it is defined by the intensities of red, green, and blue
channels.
Resolution: Resolution refers to the number of pixels in an image, typically
measured in pixels per inch (PPI). Higher resolution means more pixels and
greater detail, enhancing image clarity and quality.
Color Channels: In RGB images, each pixel is composed of three-color
channels (red, green, blue). The combination of these channels at varying
intensities produces a wide range of colors. High-quality images require
accurate representation of these color channels.
Collective Impact: High pixel values, resolution, and well-defined color
channels contribute to a detailed, sharp, and color-rich image. Lower values or
resolution can result in blurred, pixelated, or distorted images, reducing visual
quality and effectiveness in Computer Vision tasks.

3. Computer Vision has evolved from basic image processing techniques to

advanced AI-driven algorithms that can understand and interpret complex visual
data. This evolution has had a significant impact on modern technology,
enabling advancements in areas such as autonomous driving, facial recognition,
medical diagnostics, and augmented reality. As a result, many industries have
seen improved efficiency, safety, and innovation through the integration of
Computer Vision technologies.

4. Feature extraction involves identifying and isolating significant information

from an image, such as edges, textures, and shapes. This process is crucial for
various Computer Vision tasks:
Object Recognition: Features help in identifying objects within an image by
matching extracted features with known patterns.
Image Classification: Features are used to classify images into categories based
on their content.
Tracking: Extracted features allow for tracking objects across frames in video
analysis, crucial for surveillance and motion detection.
Augmented Reality: Features are used to overlay virtual objects accurately
onto real-world scenes

137
5. Object Detection: This task involves identifying and locating objects within an
image, providing bounding boxes around detected objects. It focuses on
detecting multiple objects and their positions.
Image Classification: This task assigns a single label to an entire image based
on its content. It does not provide the locations of objects, only categorizes the
image as a whole.
Image Segmentation: This task divides an image into segments, each
representing a different object or region. It provides pixel-level classification,
offering detailed information about the structure and boundaries within the
image.
Case Study/Application-Based Questions on Computer Vision- 5 marks-
Answers
1. Computer Vision helps in lane detection by using cameras to identify lane
markings on the road, ensuring the vehicle stays within its lane. Pedestrian
recognition involves detecting and tracking pedestrians to avoid collisions.
Traffic sign recognition uses image processing to identify and interpret traffic
signs, allowing the vehicle to respond accordingly. Challenges in adverse
weather conditions include reduced visibility and accuracy. These can be
mitigated by using additional sensors such as radar and LIDAR, as well as
implementing advanced algorithms to enhance image processing in poor
visibility.
2. Computer Vision algorithms can analyze medical images to detect abnormalities
like tumors by identifying unusual patterns and shapes that indicate the presence
of disease. The advantages include faster and more accurate diagnosis, early
detection of diseases, and improved treatment planning. This technology reduces
the workload on medical professionals and increases the chances of successful
treatment by identifying issues at an early stage.

3. Object detection is used to identify and monitor objects within the surveillance
area, alerting security personnel to any suspicious activity. Facial recognition
identifies individuals by comparing captured images with a database of known
faces, enhancing security by recognizing potential threats. Ethical considerations
include privacy concerns, potential biases in recognition algorithms, and the
need for transparency and accountability in how the data is used and stored.
4. Understanding pixel values helps in identifying the intensity and color
information of each pixel, which is essential for correcting damaged areas.
Resolution knowledge is important for maintaining image detail during
restoration. Color channels are used to accurately restore the colors in RGB
images. Computer Vision enhances quality by using algorithms to fill in missing
parts, correct color imbalances, and sharpen details, resulting in a restored image
that closely resembles the original.
138
5. Computer Vision can track inventory levels in real-time by analyzing shelf
images, ensuring timely restocking. It can analyze customer behavior by
monitoring movement patterns and product interactions, helping in optimizing
store layout and marketing strategies. Automated checkout systems use image
recognition to identify products and streamline the payment process. Benefits
include increased efficiency, reduced labor costs, and improved customer
satisfaction. Challenges include the high cost of implementation, potential
technical issues, and ensuring data privacy and security.

139