MauryaHub PYQ Practice

Deep Learning for Computer Vision · Quiz 1 · Jan 2024

Deep Learning for Computer Vision · Quiz 1 · Jan 2024

← Course papers · Start practice / exam

Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.

0 / 23 published solutions

Question 159 MCQ · 2.0 marks

Source diagram or notation
6406532474450.
1→ ii, 2→ ii, 3 → iv, 4→ i
6406532474451.
1→ ii, 2→iv, 3 → i, 4→ iii
6406532474452.
1→ ii, 2→ ii, 3 → iv, 4→ iii
6406532474453.
1→ ii, 2→ iv, 3 → v, 4→ iii

A published solution is not available for this question yet.

Report a correction for Q159

Question 160 MCQ · 2.0 marks

Which of the following statements is True
6406532474460.
Gaussian filter is Separable filter because it is non linear.
6406532474461.
Median filter is a non separable filter
6406532474462.
Gaussian filter is a High Pass filter.
6406532474463.
Mean filter is a non separable filter because it is non linear

A published solution is not available for this question yet.

Report a correction for Q160

Question 161 MCQ · 2.0 marks

Which of the following statements is false regarding SIFT and SURF?
6406532474464.
SIFT and SURF are two most useful approaches to detect and match features because they are invariant to scale, rotation, translation, illumination, and blur
6406532474465.
SURF is better than SIFT in rotation invariance, blur and warp transform
6406532474466.
SURF is 3 times faster than SIFT because of its use of integral image and box filter
6406532474467.
descriptors with dimensions lower than 128 perform pretty well across a range of matching tasks

A published solution is not available for this question yet.

Report a correction for Q161

Question 162 MCQ · 2.0 marks

Identify the correct sequence of steps in a Canny edge detection pipeline. Steps listed below: 1. Compute gradient magnitude and direction 2. Connect individual components 3. Smoothen the image 4. Non-maximum suppression along the edge 5. Threshold into strong, weak or no edge 6. Non-maximum suppression perpendicular to the edge
6406532474468.
3→ 1→ 4→ 5 → 2
6406532474469.
3→ 5→ 1→ 4 → 2
6406532474470.
3→ 1→ 6→ 5 → 2
6406532474471.
3→ 1→ 5→ 6 → 2

A published solution is not available for this question yet.

Report a correction for Q162

Question 163 MCQ · 2.0 marks

Source diagram or notation
6406532474479.
1→iii, 2 → iv, 3→ i,4→ v
6406532474480.
1→ii, 2→i, 3→iv,4→iii
6406532474481.
1→iii, 2→i, 3→iv,4→ii
6406532474482.
1→iv, 2→i, 3→iii,4→ii

A published solution is not available for this question yet.

Report a correction for Q163

Question 164 MCQ · 2.0 marks

In RANSAC, what is the probability that the algorithm never selects a whole set of inliers from 20 data points (which has 5 inliers in total) for k = 2 time steps? Here, n = 2 is the minimum number of samples to fit a model.
6406532474487.
0.2
6406532474488.
0.93
6406532474489.
0.87
6406532474490.
0

A published solution is not available for this question yet.

Report a correction for Q164

Question 165 MCQ · 2.0 marks

Suppose we have a codebook of 2048 SIFT visual words. We extract 1000 SIFT descriptors (SIFT is a 128-dimensional feature) from a new image. What is the dimensionality of the BoW (Bag-of-Words) descriptor?
6406532474491.
1000
6406532474492.
128
6406532474493.
128 × 2048
6406532474494.
2048

A published solution is not available for this question yet.

Report a correction for Q165

Question 166 MCQ · 2.0 marks

Source diagram or notation
6406532474495.
1→ iii, 2→ ii, 3 → iv, 4→ i
6406532474496.
1→ v, 2→i, 3 → iv, 4→ iii
6406532474497.
1→ iii, 2→ i, 3 → ii, 4 →v
6406532474498.
1→ ii, 2→ v, 3 → iv, 4→ iii

A published solution is not available for this question yet.

Report a correction for Q166

Question 167 MSQ · 2.0 marks

Which of the following linear filters will leave the central value of the given matrix unchanged.
Source diagram or notation
6406532474456.Source diagram or notation
6406532474457.Source diagram or notation
6406532474458.Source diagram or notation
6406532474459.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q167

Question 168 MSQ · 2.0 marks

Which of the following statements are True?
6406532474475.
LoG Filter is not appropriate to be used for blob detection.
6406532474476.
Image patches with large contrast changes (gradients) are easier to localize.
6406532474477.
Gradients in at least two (significantly) different orientations are the hardest (e.g., corners) to detect.
6406532474478.
In case of ‘Hysteresis Thresholding’, if gradient at a pixel is greater than high threshold that means it is an edge pixel.

A published solution is not available for this question yet.

Report a correction for Q168

Question 169 NAT · 2.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q169

Question 170 NAT · 2.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q170

Question 171 NAT · 2.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q171

Question 172 NAT · 2.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q172

Question 173 NAT · 2.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q173

Question 174 SHORT_TEXT · 1.0 marks

In case of template matching by using correlation, even if template is not identical to some subimage in the scene, match can be meaningful, if (a) _____________ , (b) _____________ and general appearance is right. Based on the above data, answer the given subquestions.
Enter the correct answer for Blank (a) ______________ .

A published solution is not available for this question yet.

Report a correction for Q174

Question 175 SHORT_TEXT · 1.0 marks

In case of template matching by using correlation, even if template is not identical to some subimage in the scene, match can be meaningful, if (a) _____________ , (b) _____________ and general appearance is right. Based on the above data, answer the given subquestions.
Enter the correct answer for Blank (b) ______________ .

A published solution is not available for this question yet.

Report a correction for Q175

Question 176 NAT · 0.5 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
a11 = ____________

A published solution is not available for this question yet.

Report a correction for Q176

Question 177 NAT · 0.5 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
a12 = ____________

A published solution is not available for this question yet.

Report a correction for Q177

Question 178 NAT · 0.5 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
a21 = ____________

A published solution is not available for this question yet.

Report a correction for Q178

Question 179 NAT · 0.5 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
a22 = ____________

A published solution is not available for this question yet.

Report a correction for Q179

Question 180 NAT · 1.0 marks

The degrees of freedom for translation and affine transformations are (a) __________ and (b) ___________ respectively. Based on the above data, answer the given subquestions.
Enter the correct answer for blank (a) __________.

A published solution is not available for this question yet.

Report a correction for Q180

Question 181 NAT · 1.0 marks

The degrees of freedom for translation and affine transformations are (a) __________ and (b) ___________ respectively. Based on the above data, answer the given subquestions.
Enter the correct answer for blank (b) __________.

A published solution is not available for this question yet.

Report a correction for Q181