Pre-deep learning

Question 1

What is the primary goal of Principal Component Analysis (PCA)?

A) To increase the number of features in the dataset
B) To reduce the dimensionality of the dataset while retaining most of the variance
C) To perform image segmentation
D) To apply convolution to the dataset

Answer 1

B) To reduce the dimensionality of the dataset while retaining most of the variance

Question 2

Which of the following is a global feature descriptor used in image analysis?

A) SIFT
B) HOG
C) Color histogram
D) SURF

Answer 2

C) Color histogram

Question 3

What is the main advantage of using local features like SIFT or SURF in image processing?

A) They are invariant to scale, rotation, and illumination changes
B) They are simple to compute
C) They require no preprocessing
D) They reduce the image to a single feature vector

Answer 3

A) They are invariant to scale, rotation, and illumination changes

Question 4

In the context of color spaces, what does HSV stand for?

A) Hue, Saturation, Value
B) Hue, Sharpness, Vibrance
C) High, Standard, Vivid
D) Hue, Saturation, Vividness

Answer 4

A) Hue, Saturation, Value

Question 5

Which of the following is NOT a property of PCA?

A) Orthogonality of principal components
B) Maximizing variance along the axes
C) Minimizing the reconstruction error
D) Maximizing correlation between components

Answer 5

D) Maximizing correlation between components

Question 6

What technique is commonly used to extract texture features from an image?

A) Histogram equalization
B) Co-occurrence matrices
C) Gaussian filtering
D) PCA

Answer 6

B) Co-occurrence matrices

Question 7

What is the purpose of using the Lab* color space in image processing?

A) To separate the luminance and chromaticity components for better color manipulation
B) To represent images in binary format
C) To enhance the texture features
D) To perform edge detection

Answer 7

A) To separate the luminance and chromaticity components for better color manipulation

Question 8

How does the Gabor filter function in texture analysis?

A) It enhances edges in the image
B) It captures both spatial and frequency information for texture representation
C) It performs histogram equalization
D) It reduces the image noise

Answer 8

B) It captures both spatial and frequency information for texture representation

Question 9

What is the main use of eigenvalues and eigenvectors in PCA?

A) To perform image convolution
B) To compute the Fourier transform
C) To identify the principal components and their significance
D) To segment the image

Answer 9

C) To identify the principal components and their significance

Question 10

Which feature descriptor is based on the distribution of gradient orientations in localized portions of an image?

A) SIFT
B) HOG (Histogram of Oriented Gradients)
C) LBP (Local Binary Patterns)
D) SURF

Answer 10

B) HOG (Histogram of Oriented Gradients)

Question 11

Question: PCA reduces the dimensionality of data by projecting it onto the eigenvectors corresponding to the largest eigenvalues.

A) True
B) False

Answer 11

A) True

Question 12

Local Binary Patterns (LBP) are a texture descriptor that captures the spatial structure of local image texture.

A) True
B) False

Answer 12

A) True

Question 13

The RGB color space is often preferred over HSV for color-based segmentation tasks.

A) True
B) False

Answer 13

B) False

Question 14

The primary advantage of using PCA is that it makes the data more interpretable by maximizing the variance along the principal components.

A) True
B) False

Answer 14

A) True

Question 15

The co-occurrence matrix method is used to extract shape features from an image.

A) True
B) False

Answer 15

B) False

Question 16

The SIFT algorithm is robust to changes in scale and rotation but not to illumination changes.

A) True
B) False

Answer 16

B) False

Question 17

In the Lab* color space, ‘L’ represents the lightness component, while ‘a’ and ‘b*’ represent the color-opponent dimensions.

A) True
B) False

Answer 17

A) True

Question 18

Gabor filters are used for texture analysis because they provide a joint representation of spatial and frequency information.

A) True
B) False

Answer 18

A) True

Question 19

Eigenvectors in PCA are orthogonal to each other.

A) True
B) False

Answer 19

A) True

Question 20

The principal components in PCA are the directions in which the variance of the data is maximized.

A) True
B) False

Answer 20

A) True

Question 21

Which of the following algorithms is used for edge detection by calculating the gradient of the image intensity?

A) SIFT
B) Canny
C) HOG
D) SURF

Answer 21

B) Canny

Question 22

In image processing, what is the primary purpose of the Sobel operator?

A) Texture analysis
B) Color segmentation
C) Edge detection
D) Image smoothing

Answer 22

C) Edge detection

Question 23

What does the term “eigenface” refer to in facial recognition?

A) A method for facial landmark detection
B) The eigenvectors used in PCA for face recognition
C) A filter used in image preprocessing
D) A type of convolutional filter

Answer 23

B) The eigenvectors used in PCA for face recognition

Question 24

Which feature extraction method is specifically designed to be invariant to affine transformations?

A) SIFT
B) HOG
C) LBP
D) PCA

Answer 24

A) SIFT

Question 25

What does the term "texture" in an image refer to? A) The color composition of an image B) The variation in pixel intensity C) The spatial arrangement of pixel intensities D) The edges within an image

Answer 25

C) The spatial arrangement of pixel intensities

Question 26

Which of the following color spaces is perceptually uniform, meaning that a change of the same amount in a color value should produce a change of about the same visual importance? A) RGB B) HSV C) Lab* D) CMYK

Answer 26

C) Lab*

Question 27

Which method of feature extraction involves computing a histogram of gradient orientations within a localized region of an image? A) HOG B) SIFT C) SURF D) LBP

Answer 27

A) HOG

Question 28

What is the main purpose of using color histograms in image analysis? A) To enhance image resolution B) To represent the color distribution of an image C) To detect edges D) To perform texture analysis

Answer 28

B) To represent the color distribution of an image

Question 29

Which feature descriptor is based on comparing each pixel with its neighbors and encoding the result as a binary pattern? A) HOG B) SIFT C) LBP (Local Binary Patterns) D) SURF

Answer 29

C) LBP (Local Binary Patterns)

Question 30

In PCA, the principal components are the eigenvectors of which matrix? A) The image matrix B) The covariance matrix of the data C) The Fourier transform of the image D) The gradient matrix

Answer 30

B) The covariance matrix of the data

Question 31

The RGB color space is often preferred for tasks involving color manipulation and color-based segmentation due to its perceptual uniformity. A) True B) False

Answer 31

B) False

Question 32

The Gabor filter is primarily used for edge detection in image processing. A) True B) False

Answer 32

B) False

Question 33

Local Binary Patterns (LBP) is a texture descriptor that is rotation invariant. A) True B) False

Answer 33

B) False

Question 34

The principal components in PCA are orthogonal to each other, ensuring that each component captures unique variance in the data. A) True B) False

Answer 34

A) True

Question 35

Co-occurrence matrices are used to capture color information in an image. A) True B) False

Answer 35

B) False

Question 36

Histogram equalization is a technique used to improve the contrast of an image by adjusting the intensity distribution. A) True B) False

Answer 36

A) True

Question 37

PCA can be used for noise reduction by projecting the data onto the principal components and reconstructing it with fewer components. A) True B) False

Answer 37

A) True

Question 38

The SIFT algorithm detects and describes local features in images, making it robust to scale and rotation changes. A) True B) False

Answer 38

A) True

Question 39

The term "eigenvalue" in PCA represents the variance captured by its corresponding eigenvector. A) True B) False

Answer 39

A) True

Question 40

The HSV color space is often used for tasks that involve human perception of colors, as it separates color information (hue) from intensity (value). A) True B) False

Answer 40

A) True