bleh

Question 1

(T/F)Increasing the number of samples within a fixed range results in higher resolution.

Answer 1

True

Question 2

A grayscale image has three different color channels for every pixel.

Answer 2

False

Question 3

The morphological opening of an image is simply a dilation followed by an erosion.

Answer 3

False

Question 4

Watershed algorithm is used to smoothing the edges in the image.

Answer 4

False

Question 5

Canny edge detection uses alignment of the edges when detecting the edges.

Answer 5

False

Question 6

Dilation operation in morphological filters can be used removing small noisy pixels from the input image.

Answer 6

True

Question 7

In deep learning pipeline, hand-crafted features are used for classification.

Answer 7

False

Question 8

If we build a neural network with no activation function, we get a linear classifier.

Answer 8

True

Question 9

From the following list of image enhancement techniques covered in class, select the techniques to reduce noise in the original image.

Answer 9

• Median Filtering
• Weighted Average

Question 10

From the following list of image enhancement techniques covered in class, select the techniques to sharpen the edges in the original image.

Answer 10

• Laplacian
• Sobel Filter
• Unsharp Masking

Question 11

From the following list of image enhancement techniques covered in class, select the techniques to improve the contrast in the original image.

Answer 11

• Contrast Stretching
• Histogram Equalization
• Power Law

Question 12

12. In an input image, each pixel is shown with 8 bits. In order to find the type of the noise, a test pattern is cropped from a flat region in the input images and its histogram is shown. The histogram of the test pattern is shown below. What kind of noise can be estimated from this histogram?

Answer 12

Salt and Pepper

Question 13

Answer 13

Question 14

For ImageNet classification challenge, several convolutional neural networks are designed over the years to achieve better performance. Please sort the following networks from the shallowest to the deepest (from less number of layer to more number of layers).
VGG
AlexNet
ResNet

Answer 14

Question 15

In our class, we covered four different machine vision tasks using Convolutional Neural Networks.
Which task detects all objects in the image and identifies the pixels that belong to each object?

Answer 15

• Instance Segmentation

Question 16

Which components of a Convolutional Neural Network is used to reduce the dimensions of the feature maps? Thus, it reduces the number of parameters to learn and the amount of computation performed in the network.

Answer 16

Pooling

Question 17

When we visualize the first layer of a deep network, what will we see in the output of these layers?

Answer 17

Low Level features such as edges and corners

Question 18

Fill In the blank in following sentence: Generative Adversarial Networks (GANs) jointly train generator and ___________ with a minimax game.

Answer 18

Discriminator

Question 19

Select the answers in order to fill in the blanks in the following sentence:
During the backward pass, each node in the graph receives ____________ gradients and multiplies them by ____________ gradients to compute ____________ gradients.

Answer 19

Upstream, local, downstream

Question 20

Select the answers in order to fill in the blanks in the following sentence:
In the stereo cameras, we search over disparity to find the correspondence in two stereo images. The disparity of the close objects in the stereo images ___________.

Answer 20

Is larger than far objects

Question 21

Which of the following best describes optical flow in computer vison?

Answer 21

An algorithm for estimating the motion of objects in a visual scene

Question 22

Which challenge is commonly encountered when estimating optical flow in dynamic scenes?

Answer 22

Illumination changes

Question 23

What is the primary purpose of camera calibration in computer vision?

Answer 23

Correcting lens distortions

Question 24

Which parameter is NOT typically estimated during camera calibrations?

Answer 24

Image Brightness

Question 25

In Convolutional Neural Networks, some times we use “Transfer Learning”. What is Transfer Learning? In what situations, we use it? What advantages does transfer learning offer in CNNs?

Answer 25

Transfer learning is the process of using an existing model and retraining it to be used for a new purpose. Situations in which we use it are when there is a lack of training data,