Test 1 Flashcards

1
Q

What is an invariant feature

A

Values remain unchanged under specific transformations (e.g., rotation, scaling)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is a covariant feature

A

Values change predictably under transformations (e.g., scaling affects area proportionally)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is a global feature

A

Describes an entire image (e.g. colour histogram)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is a local feature

A

Applies to individual image regions (e.g., corners, edges, etc.)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Define a feature

A

A distinctive attribute or description used to label or differentiate objects in images

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is the difference between detection and description in image processing

A

Detection: Finding features
Description: Quantifying features

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

True or False: The purpose of preprocessing techniques is to prepare images for further analysis by reducing noise, enhancing features, and normalizing data

A

True

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is boundary analysis

A

Focuses on the edges or outlines of objects, aids in object shape identification

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is region analysis

A

Focuses on the areas or segments within an image, supports texture and pattern recognition

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is boundary following or boundary tracing

A

It identifies and follows the boundary of an object in a binary image

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What are the necessary inputs for boundary following and what is the output

A

Inputs/Requirements:
- Binary image padded with a border of 0’s
- Single connected region (can be extended to multiple regions)

Output: An ordered sequence of boundary points

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Define chain codes

A

Represent the boundary of an object as a sequence of connected line segments. These segments are described using directional numbers based on connectivity

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What are the connectivity types of chain codes

A

4-connectivity: Segments connect pixels in horizontal and vertical directions (up, down, left, right)

8-connectivity: Segments connect pixels in diagonal directions as well, enabling finer boundary representation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is a Freeman chain code

A

A chain code that assigns a directional number (e.g., 0 for right, 1 for top-right, etc.) to each segment between consecutive boundary pixels. An example could look like 0766666453321212 (8-connectivity system)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

True or False: Fine-grained grids can result in longer chains that may be more accurate, but could also be more susceptible to noise or segmentation errors

A

True

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Define slope chain codes (SCCs)

A

An alternative to Freeman chain codes. Uses slope changes between contiguous line segments to represent a boundary

17
Q

Define boundary approximations using minimum-perimeter polygons (MPP)

A

A boundary approximation that uses polygons minimizes the total perimeter while maintaining the shape’s integrity