Textbook Solutions: Computer Vision | Artificial Intelligence for Class 10 PDF Download

Test Yourself

Q1: What is the primary objective of the Convolution Layer in a Convolutional Neural Network (CNN)?
A) To flatten the input image
B) To assign importance to various aspects/objects in the image
C) To reduce the spatial size of the input image
D) To perform element-wise multiplication of image arrays
Ans: B) To assign importance to various aspects/objects in the image
Explanation: The convolution layer applies filters to the input image to detect important features such as edges, textures, and patterns. It helps the network focus on meaningful parts of the image.

Q2: Which of the following tasks is an example of computer vision?
A) Rescaling an image
B) Correcting brightness levels in an image
C) Object detection in images or videos
D) Changing tones of an image
Ans: C) Object detection in images or videos
Explanation: Computer vision involves understanding and interpreting visual content, such as detecting, classifying, or segmenting objects in images or videos.

Q3: How is resolution typically expressed?
A) By the number of pixels along the width and height, such as 1280x1024
B) By the brightness level of each pixel, ranging from 0 to 255
C) By the total number of pixels, such as 5 megapixels
D) By the arrangement of pixels in a 2-dimensional grid
Ans: A) By the number of pixels along the width and height, such as 1280x1024
Explanation: Resolution indicates the dimensions of an image in terms of its width and height in pixels.

Q4: What is the core task of image classification?
A) Identifying objects and their locations in images
B) Segmenting objects into individual pixels
C) Assigning an input image one label from a fixed set of categories
D) Detecting instances of real-world objects in images
Ans: C) Assigning an input image one label from a fixed set of categories
Explanation: Image classification assigns a single category or label to the entire image based on its content.

Q5: What is the function of the Rectified Linear Unit (ReLU) layer in a CNN?
A) To reduce the image size for more efficient processing
B) To assign importance to various aspects/objects in the input image
C) To get rid of negative numbers in the feature map and retain positive numbers
D) To perform the convolution operation on the input image
Ans: C) To get rid of negative numbers in the feature map and retain positive numbers
Explanation: ReLU introduces non-linearity by converting negative values to zero while keeping positive values unchanged, allowing CNNs to model complex patterns.

Q6: Object detection and handwriting recognition are examples of tasks commonly associated with:
A) Computer vision
B) Image processing
C) Both computer vision and image processing
D) Neither computer vision nor image processing
Ans: A) Computer vision
Explanation: These tasks require the AI system to interpret and understand the content of images, which is the domain of computer vision.

Q7: What does the pixel value represent in an image?
A) Width of the pixel
B) Brightness or color of the pixel
C) Height of the pixel
D) Resolution of the pixel
Ans: B) Brightness or color of the pixel
Explanation: Each pixel encodes information about its color (RGB) or intensity (grayscale) in the image.

Q8: In the byte image format, what is the range of possible pixel values?
A) 0 to 10
B) 0 to 100
C) 0 to 1000
D) 0 to 255
Ans: D) 0 to 255
Explanation: In 8-bit images, each pixel intensity is represented by a byte, ranging from 0 (black) to 255 (white or maximum intensity).

Q9: In a grayscale image, what does the darkest shade represent?
A) Total presence of color
B) Zero value of pixel
C) Lightest shade of gray
D) Maximum pixel value
Ans: B) Zero value of pixel
Explanation: In grayscale images, 0 represents black (darkest), and 255 represents white (brightest).

Q10: In an RGB image, what does a pixel with an intensity value of 0 represent?
A) Full presence of color
B) No presence of color
C) Maximum brightness level
D) Minimum brightness level
Ans: B) No presence of color
Explanation: An intensity of 0 in any of the RGB channels indicates the absence of that color, contributing to black or darker shades.

Q11: Assertion: Object detection is a more complex task than image classification because it involves identifying both the presence and location of objects in an image.
Reasoning: Object detection algorithms need to not only classify the objects present in an image but also accurately localize them by determining their spatial extent.
Options:
A) Both A and R are true and R is the correct explanation of A
B) Both A and R are true and R is not the correct explanation of A
C) A is true but R is false
D) A is False but R is true
Ans: A) Both A and R are true and R is the correct explanation of A
Explanation: Object detection combines classification (what the object is) with localization (where it is in the image), making it more complex than simple image classification.

Q12: Assertion: Grayscale images consist of shades of gray ranging from black to white, where each pixel is represented by a single byte, and the size of the image is determined by its height multiplied by its width.
Reasoning: Grayscale images are represented using a three intensities per pixel, typically ranging from 0 to 255.
Options:
A) Both A and R are true and R is the correct explanation of A
B) Both A and R are true and R is not the correct explanation of A
C) A is true but R is false
D) A is False but R is true
Ans: C) A is true but R is false
Explanation: Grayscale images use a single intensity per pixel, not three. The pixel value ranges from 0 (black) to 255 (white), and the size is determined by height × width.

Reflection Time

Q1. Imagine you have a smartphone camera app that can recognize objects. When you point your camera at a dog, the app identifies it as a dog, analyzing patterns and features in the image. Behind the scenes, the app’s software processes the image, detecting edges, shapes, and colors, then compares these features to a vast database to make accurate identifications.” Identify the technology used in the above scenario and explain the way it works.

Ans: Image recognition features are used, which are a subset of computer vision. The camera captures the image of the dog and preprocesses the image to enhance the image quality using noise reduction and correcting lighting. After that, the feature extraction helps to analyze the various features in the image, like edges, shapes, colors, and textures. This technique is known as edge detection. after that convolutional neural networks (CNNs) recognize patterns in the image and process through multiple layers.

Q2. Enlist two smartphone apps that utilize computer vision technology? How have these apps improved your efficiency or convenience in daily tasks?

Ans: The two smartphone apps are

1. Google Lens – This app helps to search for the information of any objects by simply pointing your camera at them. With the help of Google Lens, you can identify plants, landmarks, and animals and also translate the text in real-time.
2. Microsoft Seeing AI – This app helps people with visual impairments; it helps to identify objects, recognize people’s faces, and read text, etc.

Q3. How an RGB image is different from a grayscale image?

Ans: Grayscale images are images that have a range of shades of gray without apparent colour. The darkest possible shade is black, which is the total absence of colour or zero value of pixel. The lightest possible shade is white, which is the total presence of colour or 255 value of a pixel. All the images that we see around us are coloured images. These images are made up of three primary colours Red, Green, and Blue. All the colours that are present can be made by combining different intensities of red, green, and blue.

Determine the color of a pixel based on its RGB values mentioned
below:
(i) R=0, B=0, G=0
(ii) R=255, B=255, G=255
(iii) R=0, B=0, G=255
(iv) R=0, B=255, G=0

Ans:

• (i)If the color channel has minimum intensity, then by default it will be black.
• (ii) If the color channel has maximum intensity, then it will be white.
• (iii) If only Green has maximum intensity, then it will be Green.
• (iv) If only Blue has maximum intensity, then it will be Blue.

Q4. Briefly describe the purpose of the convolution operator in image processing.

Ans: Convolution is a simple mathematical operation that is fundamental to many common image processing operators. Convolution provides a way of multiplying together two arrays of numbers, generally of different sizes, but of the same dimensionality, to produce a third array of numbers of the same dimensionality.

Q5. What are the different layers in Convolutional Neural Network? What features are likely to be detected by the initial layers of a neural network and how is it different from what is detected by the later layers?

Ans: A Convolutional Neural Network (CNN) is a Deep Learning algorithm that can take in an input image, assign importance (learnable weights and biases) to various aspects/objects in the image, and be able to differentiate one from the other. The different layers of a Convolutional Neural Network (CNN) are as follows:

• Convolution Layer
• Rectified linear unit (ReLU)
• Pooling Layer
• Fully Connected Layer

It is the first layer of a CNN. The objective of the Convolution Operation is to extract the high-level features such as edges, from the input image. CNN need not be limited to only one Convolutional Layer. Conventionally, the first Convolution Layer is responsible for capturing the Low-Level features such as edges, colour, gradient orientation, etc.

Q6. “Imagine you’re a researcher tasked with improving workplace safety in a manufacturing environment. You decide to employ computer vision technology to enhance safety measures.”

Ans: Computer vision is a field of machine learning and a subset of artificial intelligence that can analyze and understand images and videos. Computer vision can be used to improve workplace safety in different ways:

• Monitoring high-risk areas: Computer vision can be used for monitoring high-risk areas in a workplace, such as equipment safety, high-risk areas, etc.
• Monitoring unsafe behaviors: Computer vision can monitor and identify the employee who is not wearing protective gear or operating equipment.
• Enhancing security: Computer vision can alert the authorities if any security threats are found in the company, for example, suspicious activity or unauthorized access.
• Emergency response: Computer vision can send an emergency message to the first department or send a message to medical emergency.

Q7. How would you utilize computer vision in two distinct applications to promote safety within the manufacturing plant, ensuring both the physical well-being of employees and the efficiency of operations? Provide detailed explanations for each application, including the specific computer vision techniques or algorithms you would employ, and how they would contribute to achieving your safety goals.

Ans: The two distinct applications of computer vision to enhance safety within a manufacturing plant are

• Safety Equipment Recognition: Computer vision can monitor the safety regulation in the company or in any other place. In computer vision, using object detection algorithm can identify whether the employee is wearing a mask or safety glasses or not.
• Safety and Security in the Workplace: Computer vision can track unauthorized users using multiple cameras. Computer vision can also use 24/7 video recording and collect evidence of criminal and non-criminal activity.

Q8. Explain the distinctions between image classification, classification with localization, object detection, and instance segmentation in computer vision tasks. Provide examples for each to support your Ans.

Ans: Distinctions between image classification, classification with localization, object detection, and instance segmentation in computer vision are –

• Classification: The image Classification problem is the task of assigning an input image one label from a fixed set of categories.
• Classification + Localisation: This is the task that 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.
• Instance Segmentation: Instance Segmentation is the process of detecting instances of the objects, giving them a category, and then giving each pixel a label based on that. A segmentation algorithm takes an image as input and outputs a collection of regions (or segments).

Q9. “Agriculture is an industry where precision and efficiency are crucial for sustainable production. Traditional farming methods often rely on manual labor and visual inspection, which can be time- consuming and error-prone. However, advancements in computer vision technology offer promising solutions to optimize various agricultural processes.

Ans: Agricultural drones equipped with high-resolution cameras and computer vision algorithms are increasingly being used to monitor crop health, detect diseases, and assess crop yields.”

Ans the following questions based on the case study mentioned above:

a. How does the integration of computer vision technology with drones improve efficiency in agricultural practices compared to traditional methods?

Ans: Integration of computer vision technology with drones improves efficiency in agricultural practices and can enhance it in several ways—

• Monitoring services: Drones can survey large areas quickly with high-resolution images.
• Precision agriculture: Drones can target specific areas for pesticides and treatment of crops.
• Real Time data: Drones can provide real time based on the condition of crop which will will help the farmer to take decision.
• Data Analytics: Data collected by drones can be analyzed using computer vision to identify patterns and trends, which will help to produce potential issues and help to improve long-term planning.

b. What are some key indicators or parameters that computer vision algorithms can analyze to assess crop health and detect diseases?

Ans: Computer vision algorithms can analyze various key indicators to assess crop health and detect diseases.

• Color Variation: Computer vision can identify the change in leaf color and be able to find the nutrient or disease deficiencies in the plant.
• Leaf shapes and size: Computer vision can identify the shape and size of the leaf, which helps to identify the signs of disease or poor crop health.
• Thermal Imaging: Computer vision algorithms can use thermal cameras to detect temperature variations in corps.

Q10. Explain the term resolution with an example.

Ans: Resolution of an image refers to the number of pixels in an image, across the width and height. For example a monitor resolution of 1280×1024. This means there are 1280 pixels from one side to the other, and 1024 from top to bottom.