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

What ist he main challenge the visual system is faced with?

A

Quick identification of any object at any size, orientation, location etc

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

What are Gestalt’s laws of - like what are tehy for?

A

Perceptual organisation

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

What are Gestalt’s 5 main rules

A 
Similarity
Common fate - same direction
Proximity
Good continuation - same path
Pragnanz - 'good form
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is the basis of the Pragnanz rule?

A

Koffka (1935) – of several possible geometrical organisations the one that willl actually occur posseses the best, simplest and most stable shape

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

Who came up with the new gestalt laws?

A

Palmer and Rock

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

What were the new gestalt laws?

A

Common region - same region of space
Connectedness
Synchrony - occur at same time

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

TWo limitations of Gestalt approach?

A

Doesn’t relaly explain how we perceive objects, more just a description of perceptual process and perceptual phonemona
Difficult to say sometimes what constitutes ‘simplest’/’best’ or what ‘good continutation’ is

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

What is the next advancement from Gestalt’s approach?

A

Triesman’s Feature Integration Theory

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

what is the order of events in Triesman’s view?

A

Object – identify primitives – combine primitives – perceive object – compare to memory – identify object if match

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

Where does attention come in or not come in in Triesman’s theory?

A

Identify primitives = pre-attnetive

Combining primitives = focused attention

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

What is Triesmans’ theory based on?

A

Feature ‘primitives’ – combine to make defined object

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

What are teh two main ways of determining primitives?

A

Image segmentation – 2 regions contianing different primitives - boundary will appear
Pop- out – if efficiecy of visual search = independetn of no of items presented = pop out

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

What are some examples of identified primtiives?

A

Curvature, tilt, colour, line crossings, line ends, movement

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

What can explain illusory conjuctions with regard to visual primitives?

A

Primtiveis = procesed independently

If stimulus possesses 2 primtivie features = sometimes combined inappropriately

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

Disadvantage of Triesman approach?

A

Largely tell us how we might combine features as opposed to how we recognise objects

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

Advantages of Triesman approach?

A

Basis of feature combining and role of attention in object recognittion

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

What are the two main models of object recognition

A

Bannerman Recognition by Component model

Marr’s computation approach

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

What does BAnnerman’s model involve>

A

It uses 36 simple geometric primitives to recognise complex objects

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

WHat are three poroperties of geons?

A

View invariance - can be recognised from almost all angles
Discriminability - can tell one from another from almost all angles
Resistant to visual noise

20
Q

What are geons defined by/

A

Properties that dont change from view to view e.g. brick = 3 parallel edges, inner y vertex and 3 outer arrow vertices

21
Q

How does Biederman’s model work? STeps?

A

Edge extraction – detection of non-accidental properties – parsing of regsions of concavitiy — determination of components – matching of components to object representation

22
Q

What happens once an image has been parsed up?

A

You can detect the accidental propetires in each of the volumetric shapes to idetnify each geon. When geons can be extracted - subject can be recognised

23
Q

What evdience is htere with regard to the importance of regions of concavities?

A

Biederman (1987) – removal of controus defining concavitities affects object recogntion.
No RoC = 50% recognition accuracy. Just RoC = 70%
Full pic = 100%

24
Q

What can priming tell us about this model and who’s experiment showed us this?

A

Biederman & Cooper, 1991 – Pic for 500ms, 7 minutes, pic for 200ms. If pic 1 and pic 2 have same geons, then raction time will be faster when looking at 2nd pic. If they are sam object but with different geons, no priming takes place (semantic priminng does but no visual priming)

25
Q

What is priming?

A

ACtivating a representation once makes it easier to use subsequently

26
Q

3 limitations of Biederman approach?

A

different types of same object —> Goldstein 2010 – may bneed to be defined to show how to distinguish between faces = same features, look different
Neurons can distinguish between much smaller than neurons
No direct evidence for geons, only evidence of interpetation of this kind

27
Q

What is the approach re computers?

A

Marr’s Computational Appraoch

28
Q

How did MArr make his appraoch?

A

Based on how a computer would recognise objects – then compared to what humans are thought to do

29
Q

What are the elements of Marr’s approach?

A

Image – primal sketch – 2.5d image/sketch – 3D model description – object catalogue

30
Q

How do you get from image to primal sketch?

A

Find contours – best way = find second derivative - where rate of change of rate of change = zero. Zero crossings = simple cells detect them.
another way – where rate of change of brightness = maximum = edge = not economical way of finding them

31
Q

How do you get from primal sketch to 2.5d image?

A

Detect these zero crossings at different spatial frequencies. When you combine them all = a number of images at different spatial scales.
Find regions where zero crossings form closed loops or where the zero crossings are the same across all scales

32
Q

How do you get from 2.5D to 3D representation and what is the differnec ebteween them?

A

2.5d = viewer-centred. 3D = object centred

3D representation is developed based on a number of visual primitives derived from carving up the visual image

33
Q

Who did an experiment on the formation of the 3D sketch?

A

Marr & Nishikara (1978)

34
Q

What did Marr & Nishikara find?

A

Development of 3D sketch = based on processing of more elementary shaped primitives
Hierarchical organisation of primitives
Concavities are importatn in segmenting parts
Through splitting up images you get generalised cones not geons
3D model representaions = same regardless of viewpoint (object centred)

35
Q

What does Recognition involve in Marr’s experiment?

A

Matching 3D model against a catalogue of stored 3D representations

36
Q

What can help to distinguish between object classes in Marr’s view?

A

Lengths and arrangement of cones could distinguish between object classes

37
Q

Two problems with Both Biederman and Marr’s models?

A

only really talking about basic level object recognition

Quite different to have a model to allow you to distinguish different exemplars in same calss

38
Q

Who had a pretty pessimistic view on current object recognition models?

A

Tarr & Vuong (2002) “The truth is, at present, that no single model can explain”….

39
Q

Was Marr’s work finished?

A

No, much of his work was unfinished when it was put together.

40
Q

What is it called if we can recognise an object from it geons?

A

PRinciple of componentail recovery

41
Q

What is the principle of coponential recovery?

A

Recognising an object from its geons

42
Q

Who provided evidnce of objects nto being enocded as a whole?

A

Golcu & Gilbert (2009) –Novel objects that shared a component with the trained object were identified at much higher levels than those that did not.
Objects are not represented in holistic manner but it is the individual components that are encoded

43
Q

Who concluded in support of not favouring either model?

A

MAyor (2010) - results suggests synthesis of elements of both of the 2 main theories rather than favouring one

44
Q

What do we know about the role of colour in object recognition?

A

Bramao et al, 2011 –> Meta-analysis of 35 exps – Results strongly support the content taht colour plays a role in object recognition – suggesst that role of colour should be taken into account in models of visual object recognitiion.

45
Q

What fMRI evdience do we have with regard to object recognitiion?

A

Joseph, 2001 – meta-analysis of fMRI studies. Recognition of manufactured objects activated more aspects of the ventral temporal cotex than natural objects or face recognition

46
Q

What is the downside to Joseph’s evidence>?

A

The recognition task used was also a predictor for brain activity (viewing, matching, naming)
Conc – cognitive demands of a particular recognition tasks = as predicitve of activateion patterns as is category membership

Object Recognition (1 decks)

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