Lecture 3 - Object Recognition Flashcards

Describe 2D pattern matching – template, feature & structural theories. Describe 3D object recognition – Marr & Nishihara (1978) & Biederman (1987; 1989) Consider viewpoint invariance and viewpoint dependence. Describe models of object recognition – stage model & cascade model. Explain cases of agnosia

1
Q

Template Theories of 2D Pattern Matching

A

multiple templates are held by memory
compares stimuli to templates in memory for one with GREATEST OVERLAP until found match
problem of imperfect matches

cant account for the FLEXIBILITY of pattern recognition
comparison would require identical orientation/size/position of template to stimuli

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

Prototype theories of 2D pattern matching

A

modification of template matching

  • flexible templates
  • we possess AVERAGE of each characteristic - but how do we have e.g. average cat figure?
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Evidence for prototype theories of 2D pattern matching:

A

FRANKS AND BANSFORD

  • presented objects based on prototypes
  • prototype was not shown
  • but PS still confident they’ve seen prototype
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Feature theories of 2D pattern matching

A
  • pattern consists of a set of features or attributed
  • e.g. A = two lines and connecting cross bar
  • but surely we need to know relationship
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Structural descriptions of 2D pattern matching:

A
  • need to know features AND relationship of features

- how each bisecting line supports the other.

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

3D object recognition:

A
  • interpret input to visual system as coherent structures
  • must be processed to give a description
  • determine what is one object (segregate from the background and other objects) to generate structural description and match this too familiar objects in memory
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Marr’s computational approach -

A

explains this 3-D object recognition.

  • primal sketch (light intensity, edges, contours and blobs)
  • 2 1/2 D sketch (depth, motion, shading, observer-centred)
  • 3-D representation (object and relationship, observer-independent)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Marr and Nishihara (1978)

A
  • objects are made up by cylinders
  • structural relationships are expressed by hierarchical organisations of cylinders
  • each cylinder has axis and way in which others are joined are expressed as cooridnates.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Biderman (1987&1989)

A
  • objects composed of basic shapes - GEONS which are geometrical icons
  • viewpoint invariant theory - recognition using:
  • 36 different volumetric shapes
  • structural relations between parts
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

properties of GEONs:

A
  1. Curvature - points on a curve
  2. parallel - set of points in a parallel
  3. Co-termination - edges terminating in a common point
  4. symmetry
  5. co-linearity - points on a straight line
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Biederman experiment into geons:

A
  • deleted edges at points where easily reinstated or difficult to determine
  • stimuli presented for the varying time period (100 to 750msec) with 25/45/65% contour removes
  • PS were slow and inaccurate with deleted edges making object non-recognisable - good at recognisable.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Support for Biederman (1987)

A
  • Vogels, Biederman Bar and LORINCZ: found cortical neurosn in monkeys sensitive to GEONS
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

ADVANTAGES AND DISADVANTAGES OF BIEDERMAN

A

AD:
- PARSIMONIOUS - a small set of primitive shapes

DIS:

  • structure is not always key to recognition (peach/nectarine)
  • which geons
  • within-category discrimination
  • context? no top-down element
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Viewpoint dependent theory

A
  • changes in viewpoint reduce the speed and accuracy of object recognition.
  • viewpoint dependent more important for within-category discrimination
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Vanrie et al 2002

A
  • when are we viewpoint-dependent or view-point indepdennt

viewpoint dependent = complex within catgeory decisions
viewpoint invariant = easy categorical decisions

both in different contexts?

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

Issues with object recognition theories:

A
  • must address binding problem - how do we integrate different kinds of info
  • overlapping objects - how do we decide what belongs to what
17
Q

Humphreys et al 1988 model of object recogntion to name production

A

object > structuraL description > semantic representation > name representation > name

18
Q

Humphreys et al 1988 alternative cascade model

A
  • structural, semantic and name stages interact
  • both within and between stages
    makes different predictors predictions about how the subject will perform in object naming take
  • problems at one stage have a knock-on effect and there are interactions between stages
  • activations flowing through and around the system - inhibition occurs throughout too.
19
Q

Agnosia:

A
  • failure of knowledge or recognition

- visual agnosia: feature processing and memory remain intact - recognition

20
Q

Apperceptive agnosia (lateral)

A
  • problems with early processing and SHAPE EXTRACTION
  • perceptual deficit, affects visual representations directly, components of visual percept are picked up - not integrated, effects may be grade, often affected: unusual views of objects
  • may struggle to recognise object from other perspective
  • missing contours is confusing
21
Q

Associative agnosia (bilateral)

A
  • problems with later processing- (recognition)
  • visual representations intact but can’t be accessed or cued in recognition - lack of info about percept
  • normal percepts stripped of meaning
  • patients do fine on perceptual tests - but can’t access names or info about objects so bad at naming/recogntion
  • agnosics fail to experience familiarity with stimulus
  • but if give name - can accurate desribe