Scribd
Upload
13 views2 pages

Computer Vision

This document outlines the examination structure for the Computer Vision course in the IV B.Tech I Semester, including details on the exam duration, maximum marks, and question format. It consists of five units, each with multiple questions focusing on key topics such as challenges in computer vision, edge detection algorithms, texture classification, motion understanding, and recognition techniques. Students are required to answer one question from each unit, with all questions carrying equal marks.

Uploaded by

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

Computer Vision

This document outlines the examination structure for the Computer Vision course in the IV B.Tech I Semester, including details on the exam duration, maximum marks, and question format. It consists of five units, each with multiple questions focusing on key topics such as challenges in computer vision, edge detection algorithms, texture classification, motion understanding, and recognition techniques. Students are required to answer one question from each unit, with all questions carrying equal marks.

Uploaded by

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

H.T.No.

Code No: IT3517 SRGEC-R20


IV B.Tech I Semester Regular/Supplementary Examinations, December 2024
COMPUTER VISION
(Information Technology)
Time: 3 Hours Max. Marks: 70
Note: Answer one question from each unit.
All questions carry equal marks.
5 × 14 = 70M
UNIT-I
1. a) What are some of the key challenges faced in computer vision research, particularly
regarding complex visual data and accuracy? (7M)
b) How computers are vastly used in contributing research and development in various fields
of computer vision? (7M)
(OR)
2. a) What are the fundamental concepts and technologies that underpin computer vision, and
how do they contribute to achieving simple vision goals? (7M)
b) How do high-level capabilities in computer vision differ from low-level capabilities, and
what are some examples of each? (7M)
UNIT-II
3. a) How do various edge detection algorithms impact the performance of contour following
techniques in image processing? (8M)
b) What are the different techniques in which graph searching can be used for appropriate
boundary detection? (6M)
(OR)
4. a) In what ways can approximate location searching be optimized to improve object tracking
in dynamic environments? (6M)
b) How do different representations of edges influence the performance of algorithms like the
Hough Transform in curve detection? (8M)
UNIT-III
5. a) How can textures be classified into different categories based on their properties, such as
regularity and randomness? (7M)
b) Compare and contrast structural models of texel placement with statistical models of
texture representation. Which is better suited for real-world applications, and why? (7M)
(OR)
6. a) Explain texture primitives and their role in defining textures in an image. Provide
examples of common texture primitives. (7M)
b) What are the most common feature descriptors for texture in pattern recognition? Compare
the strengths and weaknesses of two different descriptors. (7M)

Page 1 of 2
UNIT-IV
7. a) Explain the concept of motion understanding in computer vision. How is motion analyzed
from a sequence of images? (7M)
b) What is the role of regularization in optical flow computation? Explain how it helps in
smoothing and reducing noise. (7M)
(OR)
8. a) Define optical flow and explain how it is used to estimate motion in image sequences.
What are the key assumptions behind optical flow? (7M)
b) How different image sequencing techniques can be used for effective motion analysis in
the field of computer vision? (7M)
UNIT-V
9. a) What is face recognition, and how does it differ from face detection? Provide examples of
real-world applications of face recognition. (7M)
b) Define instance recognition and explain how it differs from category recognition. Provide
an example scenario for each. (7M)
(OR)
10. a) Explain the role of training datasets in category recognition. Why is a large and diverse
dataset important for accurate recognition? (7M)
b) Describe the role of context in object detection and scene understanding. How does
context help improve accuracy in detecting objects? (7M)

*****

Page 2 of 2

You might also like