Make Machine See Class 12 Questions and Answers: Computer vision is a field of artificial intelligence which can understant the visual data just as human do. Students can test there knowledge with these below Questions and answers. All the Questions and answers are based on the NCERT textbook.
Make Machine See Class 12 Questions and Answers
B. Short Answer Questions
1. What is Computer Vision?
Answer: Computer vision is a field of artificial intelligence that interprets images and videos through deep learning models. Computer vision helps computer systems to understand and interpret the visual world. Computer vision is sometimes called machine vision.
2. What is the main difference between classification and detection?
Answer: Classification and detection are fundamental tasks in computer vision. Classification assigns labels to the image and helps to determine the category or class to which a single object belongs. detection analysing the entire image and drawing bounding boxes around detected objects along with assigning class labels to these boxes. The main difference between classification and detection is that classification considers the image as a whole and determines its class whereas detection identifies the different objects in the image and classifies all of them.
3. Write down any two algorithms which can be used for object detection.
Answer: In object detection, it helps to make bounding boxes around multiple objects and label them according to their particular class. Some of the object detection algorithms are:
- R-CNN (Region-Based Convolutional Neural Network)
- R-FCN (Region-based Fully Convolutional Network)
- YOLO (You Only Look Once)
- SSD (Single Shot Detector)
4. Write down the process of object detection in a single object.
Answer: In single object detection, the computer vision techniques identify and locate the image within an image or video and draw a bounding box around the object in the image. To do this task, computer vision follows the following process:
- Input: Computer vision takes input of an image which contains the target object.
- Feature Extraction: The CV algorithm, like Convolutional Neural Networks (CNNs), extracts relevant features like edges, shapes and textures of the image.
- Object localisation: The computer vision algorithm predicts the object location within the image.
- Object Classification: The computer vision algorithm identifies the category of the object, like cat, dog, etc.
- Output: Finally, the computer vision surrounded the object using a bounding box and defined the class label.
5. Write any four applications of computer vision.
Answer: Some of the applications are listed below which you might have already learned in lower classes.
- Facial recognition: Popular social media platforms like Facebook uses facial recognition to detect and tag users.
- Healthcare: Helps in evaluating cancerous tumours, identifying diseases or abnormalities. Object detection & tracking in medical imaging.
- Self-driving vehicles: Makes sense of the surroundings by capturing video from different angles around the car. Detect other cars and objects, read traffic signals, pedestrian paths, etc.
- Optical character recognition (OCR): Extract printed or handwritten text from visual data such as images or documents like invoices, bills, articles, etc
C. Long Answer Questions
1. What do you mean by Image segmentation? Explain the popular segmentations.
Answer: Image segmentation is a technique in computer vision which helps to make a mask around similar characters and helps to identify each character separately from the other. Techniques like edge detection, which works by detecting discontinuities in brightness, are used in image segmentation. There are different types of image segmentation available. Two of the popular segmentation are:
- Semantic Segmentation
- Instance Segmentation
2. Explain the challenges faced by computer vision.
Answer: The challenges faced by computer vision are:
- Analytical Issues: Images have a complexity and create challenges for computer vision to understand the image accurately.
- Clear Picture: Bad lighting and different angles can make the image challenging.
- Privacy Problem: Face recognition can create a serious privacy concern, which can break the individual’s privacy rights.
- False contents: Computer vision can create fake images or videos which can spread false information.
Competency Based Questions:
1. A group of students is participating in a photography competition. As part of the competition, they need to submit digitally captured images of various landscapes. However, one of the students, Aryan, is unsure about how to ensure the best quality for his images when digitizing them. Explain Aryan how the resolution of his images can impact their quality and detail when viewed on a computer screen or printed.
Answer: When a computer processes an image, it perceives it as a collection of tiny squares known as pixels. Pixels identify whether the image is low resolution or high resolution. Aryan has to take care of the following things whenever he is taking a picture.
- More pixels provide clearer details, which make the image clear on the screen or in the print.
- Fewer pixels lead to blur when it will enlarge on the computer screen.
- Use a high resolution camera with advanced sensors for capturing images.
- Avoid compressing the image, especially which can reduce quality.
2. The Red Fort is hosting a grand cultural event, and keeping everyone safe is top priority!
A state-of-the-art security system utilizes different “FEATURE EXTRACTION ” to analyse live video feeds and identify potential issues. Identify the feature extraction technique that can be used in the following situation.
a. A large bag is left unattended near a crowded entrance.
b. A person tries to climb over a wall near a blind spot.
c. A group of people starts pushing and shoving in a congested area.
d. A wanted person with a distinctive red scarf enters the venue.
Answer: Feature extraction involves identifying and extracting relevant visual patterns or attributes from the pre-processed image. Let’s see how the security system can handle each situation.
- Unattended Bag: The object detection technique should be used to spot bags left unattended.
- Wall Climbing: The motion tracking technique can help to identify unusual movements of someone climbing a wall.
- Pushing in a Crowd: The technique crowd behavior analysis can be used to notice that someone is pushing or shoving.
- Wanted Person: The facial recognition technique can be used to identify the person wearing a red scarf.
Disclaimer: We have taken an effort to provide you with the accurate handout of “Make Machine See Class 12 Questions and Answers“. If you feel that there is any error or mistake, please contact me at anuraganand2017@gmail.com. The above CBSE study material present on our websites is for education purpose, not our copyrights. All the above content and Screenshot are taken from Artificial Intelligence Class 12 CBSE Textbook, Sample Paper, Old Sample Paper, Board Paper and Support Material which is present in CBSEACADEMIC website, This Textbook and Support Material are legally copyright by Central Board of Secondary Education. We are only providing a medium and helping the students to improve the performances in the examination.
Images and content shown above are the property of individual organizations and are used here for reference purposes only.
For more information, refer to the official CBSE textbooks available at cbseacademic.nic.in