You are on page 1of 8

NPTEL Online Certification Courses

Indian Institute of Technology Kharagpur

Deep Learning
Assignment- Week 1
TYPE OF QUESTION: MCQ/MSQ
Number of questions: 10 Total mark: 10 X 2= 20
______________________________________________________________________________

QUESTION 1:
Signature descriptor of an unknown shape is given in the figure, can you identify the unknown
shape?

a. Circle
b. Square
c. Straight line
d. Rectangle
Correct Answer: d
Detailed Solution:
Distance from centroid to boundary is smaller for ϴ values corresponding to larger side
and higher for ϴ values corresponding to shorter side. This is true for Rectangular shape.

______________________________________________________________________________
NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 2:
Signature descriptor of an unknown shape is given in the figure, If d (𝜃) is measured in cm.,
what is the area of the unknown shape?

a. 120 sq. cm.


b. 144π sq. cm.
c. 240 sq. cm.
d. 100 sq. cm.
Correct Answer: c
Detailed Solution:
This is the signature descriptor of a rectangle. Maximum distance obtained from the graph
is 13 cm which is half of the diagonal. Minimum distance obtained from graph is 5 cm
which is half of the shorter side. So half of the larger side is given by sqrt(13*13 – 5 * 5) =
12.
So area = (2*12) * (2*5) = 240 sq. cm.
______________________________________________________________________________
NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 3:

To measure the Smoothness, coarseness and regularity of a region we use which of the
transformation to extract feature?
a. Gabor Transformation
b. Wavelet Transformation
c. Both Gabor, and Wavelet Transformation.
d. None of the Above.

Correct Answer: c
Detailed Solution:
One of the important approaches to region description is texture content. This helps to
provide the measure of some of the important properties of an image like smoothness,
coarseness and regularity of the region. We use Gabor filter and Wavelet transformation to
extract texture feature.

_________________________________________________________________________
NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 4:

Given the 5 x 5 image I (fig 1), we can compute the gray co-occurrence matrix C (fig 2) by
specifying the displacement vector d = (dx, dy). Let the position operator be specified as (1, 1),
which has the interpretation: one pixel to the right and one pixel below. (Both the image and
the partial gray co-occurrence is given in the figure 1, and 2 respectively. Blank values and ‘x’
value in gray co-occurrence matrix are unknown.)

2 0 2 0 1

0 1 1 2 2

0 1 2 2 1

1 2 2 0 1

1 0 1 2 0

Fig1:

Fig 2: Matrix C

What is the value of ‘x’?

a. 0

b. 1

c. 2

d. 3

Correct Answer: a
NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

Detailed Solution:

Complete the matrix and find the central element. Value of x is 0

QUESTION 5:
Given the 5 x 5 image I (fig 1), we can compute the gray co-occurrence matrix by specifying the
displacement vector d = (dx, dy). Let the position operator be specified as (1, 1), which has the
interpretation: one pixel to the right and one pixel below. What is the value of maximum
probability descriptor?

2 0 2 0 1

0 1 1 2 2

0 1 2 2 1

1 2 2 0 1

1 0 1 2 0

Fig1

a. 3/16

b. 1/4

c. 3/12

d. 1/3

Correct Answer: b

Detailed Solution:

Maximum probability = max (cij). cij is normalized co-occurrence matrix = 4/16 = 1/4.

______________________________________________________________________________
NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 6:
Which of the following is a region descriptor?

a. Polygonal Representation
b. Fourier descriptor
c. Signature
d. Intensity histogram.

Correct Answer: d

Detailed Solution:

Histogram is a region descriptor.

______________________________________________________________________________

QUESTION 7:
We use gray co-occurrence matrix to extract which type of information?
a. Boundary
b. Texture
c. MFCC
d. Zero Crossing rate.
Correct Answer: b
Detailed Explanation: We use different feature from the gray co-occurrence matrix to
determine the textural content of an image region.
______________________________________________________________________________
NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 8:
A single card is drawn from a standard deck of playing cards. What is the probability of that a
heart is drawn or a 5?
(Hints: A standard deck of 52 cards has 4 suits namely heart, spades, diamonds and clubs)
a. 3/13
b. 4/13
c. 17/52
d. 19/52
Correct Answer: b
Detailed Solution:
Probability of drawing heart = 13/52, Probability of drawing 5 = 4/52
Probability of 5 being a heart = 1/52

Total probability of drawing a heart or 5 = 13/52 + 4/52 - 1/52 =16/52 =4/13


______________________________________________________________________________

QUESTION 9:
which of following is strictly true for a two-class problem Bayes minimum error classifier?
(The two different classes are ω1 and ω2, and input feature vector is x)
a. Choose ω1 if P(x/ω1) > P(x/ω2)
b. Choose ω1 if P(ω1)>P(ω2)
c. Choose ω2 if P(ω1/x)>P(ω2/x)
d. Choose ω1 if P(ω1/x)>P(ω2/x)
Correct Answer: d
Detailed Solution: Please refer to the video lecture
______________________________________________________________________________

QUESTION 10:
Consider two class Bayes’ Minimum Risk Classifier. Probability of classes W1 and W2 are, P (ω1)
=0.2 and P (ω2) =0.8 respectively. P (x| ω1) = 0.75, P (x| ω2) = 0.5 and the loss matrix values are
𝜆 𝜆12
[ 11 ]
𝜆21 𝜆22

If the classifier assigns x to class W1, then which one of the following is true for all values of 𝜆𝑖𝑗 .
NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

𝜆21 −𝜆11
a. < 2.67
𝜆12 −𝜆22

𝜆21 −𝜆11
b. > 1.5
𝜆12 −𝜆22

𝜆21 −𝜆11
c. < 1.5
𝜆12 −𝜆22

𝜆21 −𝜆11
d. > 2.67
𝜆12 −𝜆22

Correct Answer: d

Detailed Solution:

𝜆21 − 𝜆11 𝑃(𝜔2 ⁄𝑥)


>
𝜆12 − 𝜆22 𝑃(𝜔1⁄𝑥)
Now, P(ω1/x) = P (ω1)* P (x| ω1) / P(x) = 0.2*0.75 / P(x) = 0.15 / P(x)

P(ω2/x) = P (ω2)* P (x| ω2) / P(x) = 0.8*0.5 / P(x) = 0.4 / P(x)


𝜆21 −𝜆11
> 0.4/0.15 = 2.67
𝜆12 −𝜆22

************END***********

You might also like