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:
Which of the following is (are) region descriptor(s) ? Choose the correct option.
I) Fourier descriptor II) co-occurrence matrix III) Intensity histogram IV ) Signature

a. Both I and IV
b. Only I
c. Both II and III
d. None of the above

Correct Answer: c

Detailed Solution:

Histogram and co-occurrence matrix are region descriptors.

______________________________________________________________________________

QUESTION 2:
Consider a two class Bayes’ Minimum Risk Classifier. Probability of class ω1 is P (ω1) =0.4 . P (x|
ω1) = 0.65, P (x| ω2) =0.5 and the loss matrix values are
11 12  0.1 0.9 
    0.85 0.15
 21 22  

Find the Risk R (α1|x).

a. 0.51

b. 0.61

c. 0.53

d. 0.39

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

Detailed Solution:
P (ω2 ) = 1 - P (ω1 ) = 0.6

R(α1 |x) = λ11 * P(ω1 /x)+ λ12 * P(ω2 /x)

Where, P(ω1 /x) = P (ω1 )* P (x| ω1 ) / P(x) and P(ω2 /x) = P (ω2 )* P (x| ω2 ) / P(x)

Now, P(x) = P (ω1 )* P (x| ω1 ) + P (ω2 )* P (x| ω2 ) = 0.4*0.65 + 0.6*0.5 = 0.56

P(ω1 /x) = P (ω1 )* P (x| ω1 ) / P(x) = 0.4*0.65 / 0.56 = 0.464

Similarly, P(ω2 /x) = P (ω2 )* P (x| ω2 ) / P(x) = 0.6*0.50 / 0.56 = 0.536

So, R(α1 |x) = 0.1*0.464 + 0.9*0.536 = 0.53

______________________________________________________________________________
QUESTION 3:
If the larger values of gray co-occurrence matrix are concentrated around the main diagonal,
then which one of the following will be true?

a. The value of entropy will be very low.

b. The value of element difference moment will be high.
c. The value of inverse element difference moment will be high.
d. None of the above.

Correct Answer: c

Detailed Solution:

Options are self-explanatory. We can’t comment anything on the entropy based on the
values of diagonal elements. Because it depends on the randomness of the value. Whereas
element difference moment will be low and inverse element difference moment will be high.

______________________________________________________________________________

QUESTION 4:
Suppose Fourier descriptor of a shape has K coefficient, and we remove last few coefficients
and use only first m (m<K) number of coefficients to reconstruct the shape. What will be effect
of using truncated Fourier descriptor on the reconstructed shape?

a. We will get a smoothed boundary version of the shape.

b. We will get only the fine details of the boundary of the shape.
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

c. Full shape will be reconstructed without any loss of information.

d. Low frequency component of the boundary will be removed from contour of the
shape.

Correct Answer: a

Detailed Solution:

Low frequency component of Fourier descriptor captures the general shape properties of
the object and high frequency component captures the finer detail. So, if we remove the last
few components, then the finer details will be lost, and as a result the reconstructed shape
will be smoothed version of original shape. The boundary of the reconstructed shape will
be a low frequency approximation of the original shape boundary.

______________________________________________________________________________

QUESTION 5:
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. Cannot be predicted
Correct Answer: a
Detailed Solution:
Distance from centroid to boundary is same for every value of ϴ. This is true for Circle
with a radius k.
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 6:
Signature descriptor of an unknown shape is given in the figure. If the value of k is 7 cm., what
is the area of the unknown shape

a. 145 sq. cm.

b. 49 sq cm.
c. 98 sq cm.
d. 154 sq cm.
Correct Answer: d
Detailed Solution:
Distance from centroid to boundary is same for every value of ϴ. This is true for Circle
with a radius k. So, with radius 7 cm., area of the circle is 154 sq. cm.

______________________________________________________________________________

QUESTION 7:
Which of the following is not a Co-occurrence matrix-based descriptor?

a. Entropy
b. Uniformity
c. Intensity histogram.
d. All of the above.

Correct Answer: c

Detailed Solution:

Please follow lecture videos.

 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 8:

Given an image I (fig 1), The gray co-occurrence matrix C (fig 2) can be constructed 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’,‘Y’ values in
gray co-occurrence matrix are unknown.)

2 0 2 0 1

0 1 1 2 2

2 1 2 2 1

1 2 2 0 1

1 0 1 2 0

Fig1: I

Fig 2: C

What is the value of (Y – X) ?

a. 0

b. 1

c. 2

d. 3
Correct Answer: d

Detailed Solution:
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

Complete the matrix and find the elements. Value of X is 0, Value of Y is 3.

QUESTION 9:
What is the value of maximum probability descriptor?

a. 1/4

b. 3/12

c. 1/3

d. 3/16

Correct Answer: a

Detailed Solution:

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

______________________________________________________________________________

QUESTION 10:
The plot of distance of the different boundary point from the centroid of the shape taken at
various direction is known as

a. Signature descriptor

b. Polygonal descriptor

c. Fourier descriptor.

d. Convex Hull
Correct Answer: a

Detailed Solution:

Please refer to the lecture videos.

__________________________________________________________

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