Brainscape's Knowledge GenomeTM

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


See full index

Perception and Action > Object Recognition > Flashcards

Object Recognition Flashcards

1
Q

What are between category discriminations?

A

Determining between objects

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

How is perception of objects different for humans and computers?

A

For humans it is perception of familiar items, for computers it is perception of familiar patterns

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

Does variations in retinal image lead to the apparent size and shape of an object changing?

A

No

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

What are the challenges for object recognition?

A
  • Intra-class variations: there is lots of variation in a particular object (e.g. there are lots of different chairs and we can recognise them all as chairs)
  • Recognising objects when only part of it is visible
  • Recognising objects from different views
  • Recognising objects from unusual views
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What are template theories of 2D pattern matching?

A
  • There is a mini copy or template in the long term memory of all known patterns
  • We compare the stimuli to templates in memory for the one with the greatest overlap until a match is found
  • when we see something new we try to match it to our templates
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What are flaws with the template theory?

A
  • are there too many templates?
  • how do we decide what to store in long term memory?
  • where do we stop?
  • imperfect matches
  • it cannot account for the flexibility of pattern recognition system
  • comparison requires identical orientations, size, position of template to stimuli
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What are prototype theories?

A

Modification of the template matching theory with flexible templates. It possesses the average of each individual characteristic to create a prototype for matching. No match is perfect. A criterion for matching is needed

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

What are the flaws with the prototype theory?

A
  • how do we create it to begin with?
  • how do we create the average?
  • do we update the prototype as we go through life?
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is Franks & Bransford (1971) experiment to explain the prototype theory

A

They presented objects based on prototypes, the prototype was not shown. Yet participants were confident that they had seen the prototype. This suggests the existence of prototypes

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

What are feature theories of object recognition?

A

The pattern consists of a set of features or attributes. E.g. A = 2 straight lines and a connecting cross bar. But we also need to know about the relationship between the features

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

What are the flaws for the feature theory of object recognition?

A

When talking about more complex objects than letters it doesn’t really work?

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

What are structural descriptions?

A

They describe the nature of the components of a configuration and the structural arrangement of these parts. E.g. - Capital T = 2 parts, 1 horizontal, 1 vertical; vertical supports horizontal’ vertical bisects horizontal

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

How does 3D object recognition work?

A
  • First you must interpret input to the visual system as coherent structures, segregated from one another and from the background
  • this must be processed to give a structural description which can then be matched to the descriptions of visual objects stored in memory. If you get an adequate match then the objects feel recognisable to you
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is Marr’s computational approach an example of and what do we have to think about after?

A

It is an example of early image processing. We then have to think about how we match from what we see to what we have stored in memory

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

What is Marr & Nishihara’s theory of 3D object recognition?

A

Objects are comprised of cylinders and the structural description specifies relationships between cylinders. Each cylinder has an axis and the way in which others are joined are expressed as coordinates.

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

What are the flaws in Marr and Nishihara’s approach?

A

It doesn’t seem complex enough

17
Q

What is Biederman’s theory of 3D object recognition?

A

Objects are composed of basic shapes called GEONS (geometrical ions) such as blocks, cylinders, arcs and wedges. There are approximately 36 different volumetric shapes. There are a small number of structural relationships between GENOS:

  • relative size
  • verticality
  • centring
  • reltive size of surfaces at joints
18
Q

What is Biederman’s theory called?

A

The viewpoint invariant theory

19
Q

According to Biederman what is helpful in segmenting visual images into parts?

A

Concave parts of an object’s contour (on the edge of an object)

20
Q

What are the ‘non-accidental’ properties that Geons are specified in terms of?

A
  • Curvature: points on a curve
  • parallel: sets of points in parallel
  • co-termination: edges terminating in a common point
  • symmetry: versus asymmetry
  • co-linearity: points in a straight line
21
Q

What does the viewpoint invariant theory suggest object recognition does?

A

Use the relationship between GEONS to make up structural objects and compare it to familiar objects

22
Q

What was Biederman’s experiment in support of his viewpoint invariant theory?

A

According to his model Biederman hypothesised that forms of degradation which disrupt the basis for identifying GEONS should make objects more difficult to recognise. So Biederman deleted edges at points where easily reinstated or difficult to determine. Participants were found to be slow and inaccurate at ‘non-recognisable’ but relatively good at ‘recognisable’.

23
Q

According to the viewpoint invariant theory why does taking away points of concavity make an object more difficult to recognise?

A

It makes it more difficult to break down into constituent geons

24
Q

Give examples of support for Biederman’s theory

A
  • Vogels et al found some cortical neurons in monkeys that are sensitive to GEONS. They assessed the response of individual neurons in the inferior temporal cortex to changes in GEONS or changes in the size of an object. They found that some neurons responded more to GEON changes providing support for GEONS
25
Q

What are the advantages of the viewpoint invariant theory?

A
  • recognises the importance of the arrangement of the parts

- Parsimonious: small set of primitive shapes (not too many shapes)

26
Q

What are the disadvantages of the viewpoint invariant theory?

A
  • structure is not always key to recognition e.g. a peach versus a nectarine
  • Which GEONS (e.g. why that specific geon and not another geon)
  • within category discriminations (e.g. between chairs)
  • de-emphasise the role played by context in object recognition
  • simplifies the contribution of viewpoint-dependence
  • why are there 36 geons
  • it doesn’t provide a critical test (doesn’t say that it must be this explanation as opposed to something else)
27
Q

What do viewpoint invariant theories assume?

A

That ease of object recognition is not affected by the observer’s viewpoint

28
Q

What do viewpoint dependent theories assume?

A

Changes inviewpoint reduce the speed and/ or accuracy of object recognition

29
Q

What does evidence suggest in terms of viewpoint invariant and dependent theories?

A

That sometimes viewpoint invariant mechanisms are used and sometimes viewpoint dependent mechanisms are used. Viewpoint dependent thought to be more important for within category discriminations:

  • Viewpoint dependent: complex within category decisions
  • Viewpoint invariant: easy categorical decisions
30
Q

What is the binding problem?

A

How do we integrate different kinds of information to produce object recognition? When presented with several objects how do we decide which features or geons belong to which object

31
Q

What is Humphreys et al serial stage model of object naming?

A

Object -> structural description -> semantic representation -> name representation -> name

32
Q

According to the Humphreys model what happens with an agnosic patient?

A

If you get stuck on a structural description stage you can’t match to what you have stored in memory - objects seem unfamiliar to you

33
Q

What is a proso agnosic patient?

A

If you see a face in front of you and you can’t make a structural description then you can’t match to the face you have in front of you

34
Q

What is Humphreys et al ‘Cascade’ model?

A

Structural, semantic and name stages interact. Both within and between stages. Problems at one stage will have a ‘knock on’ effect

35
Q

What is agnosia?

A

Failure of knowledge or recognition

36
Q

What happens in visual agnosia?

A

Feature processing and memory remain intact and recognition deficits are limited to the visual modality. Alertness, attention intelligence and language are unaffected

37
Q

What is apperceptive agnosia?

A

problems with early processing (shape extraction). It is lateral. It is a perceptual deficit (it affects visual representations directly - components of visual percept are picked up but can’t be integrated)

38
Q

What is associative agnosia?

A

Problems with later processing (recognition). It is bilateral. Visual representations are intact but cannot be accessed or used in recognition. Lack of information about the percept. Patients do well on perceptual tests but can not access names or other information about objects. Agnosics fail to experience familiairty with the stimulus. When given names of objects they can generally give accurate verbal descriptions

39
Q

Can you get agnosia restricted to specific categories such as living versus non-living things?

A

Yes

Perception and Action (7 decks)

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