[go: up one dir, main page]
Scribd
Upload
74 views2 pages

Computer Vision Unsolved

The document covers various aspects of Computer Vision, including tasks like image classification, object detection, and the use of Optical Character Recognition. It includes objective questions, fill-in-the-blanks, true/false statements, and application-based questions, highlighting the importance of machine learning and real-world applications. Additionally, it discusses assertions and reasoning related to image processing concepts.

Uploaded by

Subbu Lakshmi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
74 views2 pages

Computer Vision Unsolved

The document covers various aspects of Computer Vision, including tasks like image classification, object detection, and the use of Optical Character Recognition. It includes objective questions, fill-in-the-blanks, true/false statements, and application-based questions, highlighting the importance of machine learning and real-world applications. Additionally, it discusses assertions and reasoning related to image processing concepts.

Uploaded by

Subbu Lakshmi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Computer vision

Unsolved Questions

SECTION A (Objective Type Questions)

1. Which of the following tasks is typically associated with Computer Vision applications?
Ans
Image classification and object recognition

2. What is the core task of image classification?


Ans
Assigning an input image one label from a fixed set of categories

3. Which of the following type of data does Computer Vision primarily work with?

Ans: Video and image data

4. Which of the following is the real-world example of image processing?


Removing red-eye effects in photos
5. Object detection and handwriting recognition are examples of tasks commonly associated
with:
a. Computer Vision
b. Image processing
c. Both a and b

6.How is resolution typically expressed?

By the number of pixels along the width and height, such as 1280x1024

Fill in the blanks:

1. A .Segmentation algorithm takes an image as input and outputs a collection of regions (or
segments).

2. In the Google Translate app, Optical Character Recognition( OCR)btechnology helps


translate text by recognising words in images.

3. A pixel value of [0, 0, 255] means maximum blue intensity.

4. Instance Segmentation is the process of


division of an image into smaller objects so that the machine can identify them from the
background.
5. Facial recognition in smart homes help ensure security by allowing only trusted
individuals to enter

State whether these statements are true or false.

1. Computer Vision is limited to image processing and cannot perform tasks like object
recognition. – False

2. Machine learning algorithms are not used in Computer Vision. – False

3. Retailers use Computer Vision to track customer behaviour and optimise inventory
management. – True

4. Colour of a pixel is determined by the number of colours it represents. – True

5. Modern apps like Instagram and Snapchat heavily rely on Computer Vision to offer fun
and interactive features. – True

Competency-based/Application-based Questions

1. Autonomous drone …..


Ans:
The drone uses cameras and sensors to detect obstacles, and Computer Vision processes
this visual data in real-time to make safe flight decisions."

Assertion and Reasoning Questions

4. Assertion (A):
Object detection is a more complex task than image classification because it involves
identifying the presence and location of objects in an image.
Reason (R):
Object detection algorithms need to not only classify the objects present in an image but also
localise them by determining their spatial extent.

"Both A and R are correct and R is the correct explanation of A"

5. Assertion (A):
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.

Reason (R):
Grayscale images are represented using a three intensities per pixel, typically RGB.
A is correct but R is incorrect

You might also like