Object Recognition Flashcards

1
Q

definition of object recognition

A

the process of matching a representation of a viewed object to a representation stored in memory

not trivial because:

  • objects vary hugely in terms of image they project on our retina, due to changes in viewpoint, posture, illumination
  • object constancy
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

recognition by template matching

A
  • perceived stimuli are compared to templates stored in memory
  • if they match, the stimulus is recognised

problem:
would need a template for each variation in stimulus

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

computational approach (david marr)

A

as a problem of information processing: how is a shape represented in a way that is useful for recognition of 3D objects?

attempts to define: 1) the problem 2) steps needed to solve it

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

3 steps of computational approach

A
  1. primal sketch
    - primitive but rich description of the way in which light information changes across visual field
    - captures the important underlying structure of image, visible edges and vertices
    - not every luminance change represents an edge, not all edges associated with luminance change
  2. 2.5D sketch
    - recovery of surfaces, depth information
    - from the point of view of observer
    - doesn’t generalise to other viewpoints (viewer-centred)
  3. 3D model representation
    - recovery of volumetric parts that make up the object
    - conceptualised as generalised cones, hierarchically organised along principal axes of the object
    - independent of pov of observer (object-centred)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

evaluation of computational approach

A
  • highly influential, first attempt to lay down in a formal way, the steps necessary for recognition
  • didn’t attempt to work out how these steps would be implemented in a neural architecture: computational rather than algorithmic level
  • difficult to find evidence that 3D models of the type described by Marr really exist
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

recognition by components (biederman)

A

all objects made up of volumetric components (geons)

36 geons are sufficient to describe all objects

geon structural descriptions: objects are represented by specific geons and the relations between them

edge extraction –> parsing regions of concavity + detection of non-accidental properties –> determination of components –> matching components to object representations

parsing: sensitive to regions of concavity and spend more time looking at these regions

non-accidental properties: tolerant to changes in viewpoint, occlusion, noises
-curvature, parallel edges, co-termination of edges, symmetry, collinearity

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

biederman & cooper study

A

priming effect for complementary image, non-visual priming effect for different exemplar

The priming effect cannot be based on low level image features (specific edges and vertices), as these differed in the complementary images.
–> Has to be object components, or full object.

The priming effect is mediated by object components.
–> Less priming when the complement image shows different components.

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

evaluation of biederman’s theory

A

at the algorithmic level – i.e., how the
recognition steps could be implemented in a neural architecture.

There is evidence that people are sensitive to geon decomposition.
– i.e., objects are recognised from their constituent parts.

Categorical relations between parts are important, but the exact metric relation between them is not so critical for object recognition (but it is for face recognition).

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

issue of viewpoint

A

both marr and biederman predict viewpoint-invariant object recognition

marr: recognition relies on 3D model, object-centred
biederman: recovery of geons can be achieved from many different viewpoints due to their non-accidental properties

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

View-based theories of object recognition

A

objects recognised on the basis of stored views that we have encountered through experience

new views have to be matched to stored views

requires some form of transformation to align and match views: mental rotation, back projection

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

mental rotation

A

the act of imagining something turning around through space

  • example of mental imagery
  • ability to actively manipulate imagery

usually measured by asking people to discriminate between objects and their mirror-images presented in different orientations

shepard & metzler: mental rotation mimics real rotation through space

people take progressively longer to do the task as the objects are rotated

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

tarr & pinker (1989) study

A

takes longer to recognise as degrees from upright oreintation increases

RT decreases with practice, but increases again with surprise items

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

jolicoeur & milliken studies

A

Observers take longer to name rotated objects.
• RT is (somewhat) proportional to degree of misorientation

• The effects of viewpoint decrease with familiarity with the rotated views

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

multiple-views-plus-transformation

A

Through experience, we build up a network of views of an object
– Multiple-views-plus-transformation

Eventually this could lead to completely invariant object recognition

Nevertheless, according to view-based theories, the representations used for
recognition are viewer-centred and dependent on image features.

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

Object recognition is not achieved through mental

rotation

A

1) mental rotation vs object recognition task

Viewpoint effects were associated with increased
activity in the superior
parietal lobe vs middle and inferior temporal lobe

2) patient with damage to
the right basal ganglia who
– was impaired on a variety of tasks that required mental rotation
– but had intact recognition of rotated objects and silhouettes

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

evaluation of view-based theories of object recognition

A

“Views” are holistic representations
– i.e., parts and their relations are not able to be recovered
independently

They work remarkably well for dealing with recognition of
individual objects across viewpoints.

They have difficulty accounting for our ability to categorise new objects as members of a category.
– such generalisations would only be possible on the basis of similarity of components.