Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Object recognition > Object Recognition > Flashcards

Object Recognition Flashcards

1
Q

MIddle Vision

A

Involves perception of edges and surfaces

determins which regions of an image should be grouped together into objects.

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

Edge Detection

A

a sudden change in brightness, color, texture- also called a contour

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

Which cells are involved in edge detection?

A

Cells in V1- tuned to detect edges with different orientations and width.

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

How good is Computer based edge detection

A

Not as good as humans- sometimes they dont find enough edges or sometimes they find too much

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

What are illusary Contours?

A

An edge that we perceive that is not actually present.

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

What does middle vision find?

A
  • important edges and ignores others & edges that are not physically present
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is Gestalt Grouping?

A

A set of rules that describe when elements in an image will appear to group together.

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

What are the Gestalt Grouping Rules?

A 
Good continuation
Similarity
Proximity
Parallelism
Symmetry

Common region
Connectedness
Common fate
Synchrony

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

What is good continuation?

A

a. Elements group to form smoothly continuing lines.

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

What is similarity?

A

a. Objects that are similar to each other, group together.

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

What is proximity?

A

a. Objects that are close to each other group together.

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

What is parallelism?

A

a. Elements that are parallel group together

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

What is Symmetry?

A

a. Elements that are symmetrical to each other group together.

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

What is Common Region?

A

a. Elements perceived to be part of a larger region group together.

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

What is Connectedness?

A

a. Elements that are connected to each other group together.

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

What is common fate?

A

a. Elements that move in the same direction group together.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What is Synchrony?

A

a. Elements that change at the same time group together.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What is a perceptual committee?

A

Many different and sometimes competing principles are involved in perception.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What is the Pandemonium Model?

A

Developed by Oliver Selfridge (1959).
Perceptual committee made up of “demons”
Demons loosely represent neurons.
Each level is a different brain area.

20
Q

What are ambiguous figures?

A

A visual stimulus that gives rise to two or more interpretations of its identity or structure.
- Neckar Cube

21
Q

What are the rules of the perceptual committee?

A

Honor physics and avoid accidents.

22
Q

What is an accidental viewpoint?

A

A viewing position that produces some regularity in the visual image that is not present in the world.

23
Q

How do the perceptual committees describe accidental viewpoint?

A

Perceptual committees assume viewpoints are not accidental.

24
Q

What is figure?

A

a foreground object.

25
Q

What is ground?

A

the background.

26
Q

What is figure ground assignment?

A

The process of determining what parts of an image belong to the figure and what parts belong to the ground.

27
Q

What are the gestalt figure ground assignment rules?

A

Surroundedness
A surrounding region is likely to be ground.
Size
A smaller region is likely to be figure.
Symmetry
A symmetrical region tends to be seen as figure.
Parallelism
Regions with parallel edges tend to be seen as figure

28
Q

What is occlusion?

A

an object blocking another

29
Q

What does relatability have to do with occlusion?

A

The degree to which two line segments appear to be part of the same contour

30
Q

What is the global superiority effect?

A

The properties of the whole object take precedence over the properties of parts of the object.

31
Q

What is an non accidental viewpoint?

A

A feature of an object that is not dependent on the exact (or accidental) viewing position of the observer.

32
Q

What are some nonaccidental features?

A
  • t-junction
  • y junction
  • arrow junction
33
Q

What is the template theory?

A

The proposal that the visual system recognizes objects by matching the neural representation of the image with a stored representation of the same “shape” in the brain.

34
Q

What are some problems with the template theory?

A

You can recognize an infinite number of different shapes as the same object

35
Q

What is a structural description?

A

A description of an object in terms of the nature of its constituent parts and the relationships between those parts.

36
Q

What is recognition by components?

A

Objects are recognized by their parts and how those parts fit together

37
Q

What are geons?

A

(“geometric ions”):
3-dimensional primitives.
Any object can be built out of them.

38
Q

What is viewpoint invariance?

A

A property of an object that doesn’t change when an observer changes viewpoint.

39
Q

What are some problems with the RBC?

A

One is that object recognition is not completely viewpoint-invariant.

40
Q

Are there multiple recognition comittees?

A

Perhaps there are several object recognition processes, depending on the category level.
Entry-level category: For an object, the label that comes to mind most quickly.
Subordinate-level category: A more specific term for an object.
Superordinate-level category: A more general term for an object.

41
Q

What is prosopagnotia?

A

An inability to recognize faces.

42
Q

What is agnosia?

A

A failure to recognize objects despite being able to see them.

43
Q

What part of the brain is used in object recognition?

A

Extrastriate cortex
The region of cortex bordering V1.
Includes multiple areas involved in visual processing.

44
Q

What is the infertomporal pathway?

A

Part of the cerebral cortex in the lower portion of the brain.
Important for object recognition
Part of the “what” pathway

45
Q

What happens when the IT pathway is injured?

A

leads to agnosia

Object recognition (5 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions