Finals | Statistical Analysis and Information Entropy

Question 1

Actual amount of information included in the image that can be computed

Answer 1

INFORMATION ENTROPY

Question 2

Describes how much randomness (or uncertainty) there is in a signal or an image; in other words, how much information is provided by the signal or image.

Answer 2

INFORMATION ENTROPY

Question 3

ENTROPY is aka

Answer 3

Shannon’s Entropy (1948) or Information Entropy

Question 4

Use of the same number of bits to represent all pixels.

Answer 4

Fixed-length coding

Question 5

Fixed-length coding

In this way, when a program reads an image file it knows that the first 12–bits represent the (1) of the first pixel, the next 12–bits represent the second pixel, and so on, with no need for any (2) to represent the (3) of each pixel’s (4).

Answer 5

1. value
2. special symbol
3. end
4. data

Question 6

Uses a variable number of bits to represent pixel values.

Answer 6

Variable-length coding

Question 7

Variable-length coding

Provides short code-words for (1) characters and long code words for (2) characters.

Answer 7

1. frequent
2. infrequent

Question 8

Variable-length coding

Variability is primarily dependent on (1) of data.

Answer 8

1. frequency of occurrence

Question 9

The use of more bits that are needed to convey a given amount of information

Answer 9

Coding redundancy

Question 10

Redundant code has a number of consequences including

Answer 10

bloated source code
reduced reliability
reduced maintainability

MaRe Bloated

Question 11

Two major methods of variable-length encoding to reduce coding redundancy

Answer 11

A. Huffman coding (Huffman, 1952)
B. Arithmetic coding (Abramson, 1963)

Question 12

ENCODED vs DECODED

Answer 12

ENCODED: Compressed image
DECODED: Compressed image that had been RECONSTRUCTED

Question 13

An entropy encoding algorithm used for lossless data compression.

Answer 13

HUFFMAN CODING

Question 14

Guarantees the uniqueness of the decoding process so that a set of codes can only represent one set of image values.

Answer 14

HUFFMAN CODING

Question 15

This replaces each pixel value of an image with a special code on a one-to-one basis.

Answer 15

HUFFMAN CODING

Question 16

This replaces each pixel value of an image with a one code.

Answer 16

ARITHMETIC CODING

Question 17

The main idea behind this coding is to assign each symbol an interval.

Answer 17

ARITHMETIC CODING

Question 18

It consists of a few arithmetic operations due to its complexity is less. In terms of complexity, this is asymptotically better than the other coding.

Answer 18

ARITHMETIC CODING

Question 19

ARITHMETIC vs HUFFMAN (statistical method?)

Answer 19

ARITHMETIC: Not a statistical method
HUFFMAN: Is a statistical method

Question 20

ARITHMETIC vs HUFFMAN (Result?)

Answer 20

ARITHMETIC: Yields an optimum result
HUFFMAN: Does not yield an optimum result

Question 21

ARITHMETIC vs HUFFMAN (1 to 1 correspondence)

Answer 21

ARITHMETIC: No one-to-one correspondence b/n source symbol and code word
HUFFMAN: There is one-to-one correspondence b/n source symbol and code word

Question 22

ARITHMETIC vs HUFFMAN (example?)

Answer 22

ARITHMETIC: If a,b,c are messages, then only one unique code to entire message
HUFFMAN: If a,b,c are messages, then separate sybols are assigned

Question 23

Fourier transform pair

Answer 23

two functions f (x, y) and F(u, v)

Question 24

Enable the transformation of a two-dimensional image from the spatial domain to the frequency domain, and vice versa.

Answer 24

The Fourier and the inverse transform

Question 25

Basically, the FT provides a —

Answer 25

frequency spectrum of a signal

Question 26

For medical images utilizing multi-modalities: In the transformation model, three categories can be identified according to the associated degrees of freedom:

Answer 26

rigid, affine, and nonlinear.

Question 27

The transformation involves only reflection, translations and rotations. This sufficesto register images of rigid objects (like bones).

Answer 27

RIGID REGISTRATION:

Question 28

Preserves the parallelism of lines, but neither their lengths nor their mutual angles.

Answer 28

AFFINE TRANSFORMATION:

Question 29

It extends the degrees of freedom of the rigid transformation with scaling and shearing in each image dimension.

Answer 29

AFFINE TRANSFORMATION:

Question 30

It is an appropriate transformation model when the image has been skewed during acquisition.

Answer 30

AFFINE TRANSFORMATION:

Question 31

Allow the mapping of straight lines to curves.

Answer 31

NONLINEAR TRANSFORMATION

Question 32

The similarity measure can be calculated globally, on the entire image, or locally, on a sub-image.

Answer 32

NONLINEAR TRANSFORMATION

Question 33

Smoothness of the deformation can be achieved in different ways and the deformation can be either (1) (any deformation is allowed) or guided by an underlying physical model of material properties, such as (2) or (3)

Answer 33

1. free-form
2. tissue elasticity
3. fluid flow