SRM Institute of Science and Technology
SET A
College of Engineering and Technology
School of Computing
DEPARTMENT OF COMPUTATIONAL INTELLIGENCE
SRM Nagar, Kattankulathur – 603203, Chengalpattu District, Tamilnadu
Academic Year: 2023-2024 ODD
Test: CLAT-2 Date : 10 -10-2023
Course Code & Title: 18CSE390T Computer vision Duration: 2 periods
Year & Sem: III & 5th sem Max. Marks: 50 Marks
Part - A
(10 x 1 = 10 Marks)
Instructions: Answer all
Q. Question Marks BL CO PO *PI
No Code
1 To address the issue using Hough transform, detecting two lines 1 2 CO-2 1 1.6.1
in instances where there is only one in a given image, which of
the following actions is most likely to mitigate this problem?
a.Increase the size of the bins in the Hough transform.
b.Decrease the size of the bins in the Hough transform.
c.Sharpen the image
d.Make the image larger
A second order derivative operator can be defined as ____. 1 1 CO-2 1 1.6.1
2 a. Laplacian b. Gaussian
c. Histogram d. Sobel
3 A set of connected pixels that lie on the boundary between 1 1 CO-2 1 2.2.4
two regions are called as ................
a. point b. edge
c. color d. line
4 Find out the measure which is not used to describe a region in 1 2 CO-2 1 1.6.1
an image.
a.Mean and median of grey values
b.Minimum and maximum of grey values
c.Number of pixels alone
d.Number of pixels above and below mean
5 Sobel gradient is not good for detection of......... 1 2 CO-2 2 1.6.1
a. Horizontal lines
b. Vertical lines
c. Diagonal lines
d. Edges
6 Which of the following is the example for application of image 1 2 CO-3 2 2.2.4
subtraction?
a..MRI scan
b.CT scan
c.Mask mode radiography
d.MRI and CT Scan
7 Stiffness in internal elasticity of active contours follows ______ 1 1 CO-3 2 1.6.1
a. First order derivatives
b. Second order derivatives
c. Third order derivatives
d. Lines and points
8 ______is a segmentation method that uses energy forces and 1 1 CO-3 2 1.6.1
constraints to separate the pixels of interest from the picture.
a. Image restoration
b. Active Contours
c. Pixel
d. On the boundary of the curve
9 The____________ model is an advanced version of the snake 1 2 CO-3 2 1.6.1
model
a. gradient vector flow
b.Advance snake model
c.Balloon model
d.Geometric active contour
10 For identifying and classifying the joints in the human body 1 1 CO-3 4 1.6.1
.......... are captured as a set of coordinates for each joint.
a. Key Points
b. Pairs
c. Skeleton
d. contour
Part – B
(Answer any Four)
(4 x 5 = 20 Marks)
Instructions: Answer ALL
11 Discuss steps of Hough Transform for line detection. 5 3 CO-2 1 1.2.1
12 How can an edge of the image be detected? Discuss any edge 5 3 CO-2 1 1.2.1
detection algorithm for detecting an edge of the following
image.
13 (a)What is an active contour model? How are contours 5 3 CO-3 1 1.2.1
represented using this model?
(b)Differentiate Feature Detection and Feature Extraction.
14 Consider the image given which is 7 X 7 in size. 5 3 CO-3 1 1.2.1
’
Illustrate the steps involved in segmenting the flower from the
input image using an intelligent scissor.
15 Explain the basic operation of an active contour “Snakes” to 5 3 CO-3 1 1.2.1
approximate the perimeter of an object. Write only the expression
of its energy function. Also, briefly note the entire procedure of
finding contours in any image.
16 What is meant by Region Splitting and Region Merging? Explain 5 3 CO-3 1 1.2.1
in detail.
Part – C
(Answer any One)
(2 x 10 = 20 Marks)
17 a) Consider the below images: 10 3 CO-2 1 1.2.1
Different images of the Eifel Tower are taken from various
perspectives, with varying foreground objects. In one image, the
tower is rotated, while in another, it’s zoomed in to display one
half of it. Identify an appropriate feature matching algorithm and
elucidate its operational principle to demonstrate that the object
‘tower’ is consistent across all the images.
( OR)
b) By illustrating the working principle of a suitable keypoint
detection and a matching algorithm, explain all the
images given below are taken from the same location.
178 a)For the given confusion matrix, calculate the following. 10 3 CO-3 1 1.2.1
(i)True Positive Rate
(ii_False Positive Rate
(iii)Positive Predictive Value
(iv)Accuracy
( OR)
b)Elucidate the snake model for locating the active contours
using a band technique with suitable diagrams. Also relate the
external and internal energy level calculation formulas used
for fitting the elastic band on the object boundaries sharply.
*Performance Indicators are available separately for Computer Science and Engineering in AICTE
examination reforms policy.
Course Outcome (CO) and Bloom’s level (BL) Coverage in Questions
CO Coverage (%)
BL Coverage %
40
120
%
100
80 30
30
60 %
%
40
20 BL1 BL2 BL3
0
CO 1 CO 2 CO 3 CO 4 CO 5
Approved by the Audit Professor/Course Coordinator
