Lecture 4

Question 1

Image Filtering

Answer 1

techniques for modifying or enhancing an image

Question 2

Types of Image Filtering

Answer 2

Linear filters and Non-linear filters

Question 3

Which are the linear filters

Answer 3

image smoothing/blurring
edge detection
image sharpening

Question 4

Which are the non-linear filters

Answer 4

morphological operators (dilation,erosion)
median filter (noise reduction)
matched filters

Question 5

the value in each output pixel depends on the which values

Answer 5

the local values of neighboring pixels

Question 6

what does a non-linear filtering

Answer 6

replace each pixel by a non-linear combination of its neighbors

Question 7

what does linear filtering

Answer 7

replace each pixel by a linear combination of its neighbors

Question 8

Image Filtering Steps

Answer 8

1. move filter matrix over the image
2. multiply the corresponding image pixel
3. sum the results and store it as a new pixel value

Question 9

Image smoothing

Answer 9

replace each pixel with the average intensity of its neighbors

Question 10

cross-correlation

Answer 10

measures the similarities between two signals

Question 11

convolution

Answer 11

measures the similarities between two signals, but the filter is flipped upside-down

Question 12

which convolutions can save a lot of time

Answer 12

separable convolutions

Question 13

strides

Answer 13

skip steps at a time (for efficiancy)

Question 14

padding

Answer 14

extending the frame of an image with empty pixels, so when the kernel goes over the image we can maintain the size of the image

Question 15

why we need padding

Answer 15

allow for more space for the kernel to cover the whole image

Question 16

blurring

Answer 16

better image smoothing

Question 17

Filters used for better image filters

Answer 17

gaussian filters

Question 18

what are doing the gaussian filters

Answer 18

remove the high-spatial frequencies

Question 19

edge detection

Answer 19

edges are sudden transition of intensity and are very informative
laplacian: measures the 2nd derivative
sensitive to noise
2 filters => sober and robert filters
subtract two blurred versions of the same image

Question 20

Laplacian of Gaussian-filtered image (LoG)

Answer 20

measure of the 2nd derivative (the change) of the image

Question 21

What is shown by the 2nd derivative in Laplacian?

Answer 21

showing the magnitude of a change

Question 22

What does the output of Laplacian stands for?

Answer 22

large and positive on one side of the edge
large and negative on the other
small/zero at the edge itself

Question 23

image sharpening

Answer 23

emphasize details of images:
edges and local contrast

Question 24

what is image sharpening

Answer 24

emphasize the details of an image

Image + alpha*EdgeDetection

Question 25

dilation

Answer 25

takes the max value of all pixels in its neighborhood

Question 26

erosion

Answer 26

takes the min value of all pixels in its neighborhood

Question 27

non-linear morphological operators

Answer 27

dilation erosion

Question 28

what does the median filter

Answer 28

noise reduction

Question 29

median filter

Answer 29

replace each pixel with the median value within its neighbor

Question 30

common models for noise reduction

Answer 30

gaussian additive noise salt-pepper noise

Question 31

Mexican Hat Filter

Answer 31

indicates the shape obtained by subtracting two Gaussians (“Difference of Gaussians”) with different standard deviations. Because “Mexican hat” refers to the shape it is sometimes also used when referring to the shape of the Laplacian filter which is very similar to that of the DoG filter.