Segmentation

Question 1

what are the four stage of image processing

Answer 1

image acquisition, when photons are converted into a matrix of numbers
pre-processing, used to correct image acquisition default or enhance image quality in order to facilitate…
the segmentation, that split the image into an object of interest and background, then each object of interest is described by,
feature extraction, that describes shape, colour, texture, etc

Question 2

explain briefly the image segmentation

Answer 2

the segmentation is assumed to be be either a pixel belong to the object or the background in histogram segmentation is based on the idea of having range values such that the value among this range will be part of the image

Question 3

Explain the histogram-based Segmentation

Answer 3

it is a type of segmentation where all the pixels are treated the same

Question 4

Explain the image threshold , and the types of the threshold by the

Answer 4

the idea is simple such that everything below a certain value T is 1 otherwise it is 0 :
T can be fixed
T can be globally adaptive in situations where we do not know exactly what is the threshold and perform a global measurement
T can locally adaptive depends on the neighbourhood

Question 5

what can we do in the case when we want to apply segmentation on an image that Is super noisy

Answer 5

initially performing directly segmentation, may lead to an unwanted results, so better omit the noise by using a median filter then normalize the image by the newly obtained one, to later on, apply the necessary threshold

Question 6

why do we use the several type of color RGB

Answer 6

since our brain is only capable of differentiating 255 grey levels hence, if we encode the gray level using color our brain can differentiate between the lines that are close to each other, the blue to yellow convention is for the color blind people

Question 7

what is the drawback of threshold

Answer 7

the drawback is deciding the threshold position is hard for the single curved image histogram

Question 8

how to segment a color image

Answer 8

simply we can pick a threshold per color (R or G or B )

Question 9

how to automatically choose a value for the threshold

Answer 9

we use what we call a percentile threshold, for instance, the galaxy image, if we know that 5 percent of the galaxies are covered by an image, hence we can rely on the cumulative histogram to put the threshold in the part that divide the distribution in 5 percent

Question 10

what is the optimal threshold, and explain how it works

Answer 10

used to detect the most adequate threshold for the image,
Optimal threshold: put arbitrarily the threshold value, then separate the distribution according to the threshold, then for each part compute the centroid, then update the threshold, by putting it in the middle, keep on iterating till convergence , however note in a single curved may not work very well

Question 11

is optimal threshold local or global

Answer 11

it is local since we rely on the initial threshold

Question 12

explain the OTsu threshold

Answer 12

is defined by two classes foreground and background separated by a threshold, we have the within-class variance that defines how compact it is while between class variance aims to split the two variances as much as possible, then the separability is defined through optimizing the between-class variance which should as separate as possible and within-class should be as small as possible 
the way it is used is that we  use the expression for every threshold value and we choose the optimum

Question 13

is the otsu local or global threshold

Answer 13

it is a global one since we test every threshold

Question 14

what is the entropy threshold

Answer 14

calculates the entropy below and above the threshold for each possible threshold value, then we put the threshold when the entropy is maximum

Question 15

what is the multispectral threshold

Answer 15

it considers a segmentation on each image specter then merge them together

Question 16

how to detect whether a specific region is blurred

Answer 16

generally blurred regions have low frequencies

Question 17

How can we deal with images that are characterized by different regions

Answer 17

we can compute the local entropy according to a window, when the entropy is low means we have less variation and more blurr, while higher entropy defines the sharp parts , then we perform a threshold on the entropy image and a threshold on the origin one then we combine them

Question 18

what is a border segmentation

Answer 18

it consists of a segmentation that is based on the information provided by borders, we usually enhance the border for instance using Sobel filter, so to separate the images, we say we are only interested in very sharp edge sobel >50

Question 19

what is the downside of border segmentation

Answer 19

when the border are not very closed, this mislead the algorithm

Question 20

what is region-based segmentation

Answer 20

it actually overcome the the downside of border segmentation

Question 21

what is a region growing segmentation

Answer 21

generally, we start from the point in the object and we keep on recruiting neighbouring pixels, it is composed of two phases :
the split-phase: where the image is split recursively then image if it is not homogeneous ( generally we can use the variance or the entropy to check the homogeneity of the pixels ), we split the image to 4
finally the merge phase consist of merging all the parts such that if the two grouped regions satisfies the homogeneity criterion, merge the regions

Question 22

explain the Model based segmenetation

Answer 22

Generally we know apriori the object we are looking for

Question 23

explain the hough Transform

Answer 23

Aimes to detect line segment in an image,
the idea is to transform initially the line equation in terms of theta and ru: x cos(θ)+ysin(θ)=ρ where ρ is the distance to the origin point and θ is the angle with the x axis
so each point is represented by the above line equation, now we need to detect their intersection

we initially map those lines to point in in the ru the space and then the intersection corresponds to the point they intersect in In the same space
but before applying it we should initially apply the canny edge on the image

Question 24

what is the intilligent scissors methods

Answer 24

it is a semi-automatics consisting of putting in the image then the algorithm tries to find the best path between these points

Question 25

what is the intelligent scissors methods

Answer 25

it is a semi-automatic consisting of putting points in the image then the algorithm tries to find the best path between these points, for instance using the Dijkstra algorithm, it can also be done in real-time

Question 26

in the intelligent scissors method, how can we find the best path

Answer 26

the idea is that we would assign weights to every link in the image (link between the pixels ),
the cost will be a function of several parameters, and we try to minimize the cost between two points in each computation

the search space is a graph and the cost is local , which is defined by 3 main costs ;
. we want the gradient to be as high as possible as the more we get into the inside the lower is the gradient value
. Laplacian near to 0, reflecting the edge. the gradient is perpendicular to the path

this function takes these values into account , and compute them for the whole image, to finally use the shortest path djikstra algorithm to compute to find the shortest path

Question 27

why do always use the second derivative

Answer 27

the second derivative reflects the 0 crossing in the image,meaning when we have an edge signal the second derivative reflects the 0

Question 28

what are the 3 types of segmentation

Answer 28

Histogram based segmentation
Texture based segmentation
Region growing segmentation which consist maily of finding the see point

Question 29

what is the main idea behind region growing algorithm

Answer 29

we initially need to find the seed points then we set the growing rules to finally classify the regions

Question 30

what is the sliding window how to overcome the overlapping in the sliding window
what is the region descriptor

Answer 30

Generally speaking a sliding window allow cutting the image into a rectangle
Simply add a stride
region descriptor reflects cutting the image into grid then computing some statistics for each specific region, generally, we can use the co-occurrence matrix and summarize the information in this concurrence matrix

Question 31

what are good markers in region growing algo

Answer 31

good marker should be as far as possible from borders

Question 32

explain the use case of the distance map

Answer 32

distance map helps during objected segmentation where those object are overlapped on the top of each other