Object Recognition and Face Recognition

Question 1

Define object recognition

Answer 1

The ability to perceive an objects physical properties and apply semantic attributes

Question 2

How do humans take in information?

Answer 2

Register large scale shapes and patterns AS QUICKLY AS small details

Question 3

Mechelli et al (2004) said what about bottom up vs top down?

Answer 3

That’s humans do bottom up first then top down

Question 4

How do computers perceive objects?

Answer 4

They start with pixels (small details) “bottom up” and then build up

Question 5

What are constancies?

Answer 5

What we see as the same, despite differences in dynamics

Question 6

What’s the context effect?

Answer 6

Some recognition requires an appreciation of context

Question 7

What did Oliva & Torralba (2007) say about object recognition?

Answer 7

That objects in familiar context are recognised faster

Question 8

What are the 5 steps to recognise an object?

Answer 8

1) see basic features
2) perceive organisation of features
3) perceive shape
4) compare shape to memory for knowledge
5) is the shape familiar, tap into knowledge

Question 9

What is simultangnosia?

Answer 9

The inability to perceive how parts fit together

Question 10

List the 3 models of object recognition

Answer 10

1) Template Matching
2) Feature recognition
3) Structural theories

Question 11

What is the template matching model?

Answer 11

When an individual compares the whole object to stored representations to find a match

Question 12

What is the feature recognition model?

Answer 12

Rather than focusing on the whole shape, feature models break down into critical features

Question 13

What’s Selfridges (1959) pandemonium model? Which 3 model does it come under?

Answer 13

It’s a metaphorical description of levels of processing patterns before the whole

Feature recognition model

Question 14

What’s Marr & Nishiharas (1978) model? And what 3 models does it come under?

Answer 14

There are 3 levels of object recognition

1) primal sketch (edges and contours)
2) 2.5D sketch (shading and textures)
3) 3D model

The feature recognition model

Question 15

What 3 things happen for recognition to occur?

Answer 15

1) single model axis
2) component axes
3) 3D model match (top down processing)

Question 16

What is the structural theory? Using RBC theory

Answer 16

Biederman’s recognition by components theory (1987)

Objects consist of combinations of geons
Object recognition is viewpoint invariant

Question 17

What’s greebles good for, using concavity importance?

Answer 17

Explores regions of concavity importance.

When presented with Greebles, individuals remained viewpoint dependent when recognising one even after training

Question 18

What’s dynamics of vision?

Answer 18

Focus on perception of static images by static observer

Question 19

What’s motion perception?

Answer 19

To perceive moving objects we must be able to pick up changes in stimulus over brief time intervals and recognise object in different stimuli. Humans are good at this.

Question 20

What 2 things do object recognition depend on?

Answer 20

Sensory info and prior expectation

Question 21

What plays an important role in object recognition that isn’t mentioned?

Answer 21

Context

Question 22

What are the 4 challenges of object recognition?

Answer 22

Different classes of things recognised
From different angles
Partly occluded
Fully occluded

Question 23

What 3 things make face recognition special?

Answer 23

The development
The configural processing
Mechanistic

Question 24

What’s “developmental” face recognition?

Answer 24

Newborns are orientated towards upright face stimuli

Tendency to disappear after a month then reappear again (nakamo et al, 2014)

Question 25

List the 3 types of “configural processing”. What is configural processing?

Answer 25

People respond faster when top and bottom of faces are unaligned, like they normally are.

1) first order relations that define faces
(2 eyes, nose, mouth)

2) holistic processing
(glueing features together into gestalt)

3) second order relations
(spacing among features)

Question 26

What’s a famous example of configural processing?

Answer 26

Thatcher illusion (Thompson 1980)

Inverted face in which eyes and mouth remain normal, preserve facial expressions better than truly inverted faces

Question 27

What’s “mechanistic”?

Answer 27

Special brain areas devoted to face processing

• fusiform face area (FFA)
• superior temporal sulcus (STS)
• occipital face area (OFA)

Question 28

What is object agonist? Use an example

Answer 28

Trouble recognising objects

E.g. Oliver sacks (1985) thought his wife was a hat

Question 29

Whats face agonist?

Answer 29

Trouble recognising faces

Question 30

What’s prosopagnosia?

Answer 30

Face blindness

Question 31

What are the 8 steps of face recognition as founded by Bruce & Young (1986)?

Answer 31

1) STRUCTURAL ENCODING (producing representations)
2) EXPRESSION ANALYSIS (emotional state inferred)
3) FACIAL SPEECH ANALYSIS (speakers lip movements)
4) DIRECTED VISUAL PROCESSING (specific facial info processed selectively)
5) FACE RECOGNITION UNITS (structural info about known faces)
6) PERSON IDENTITY NODES (provide info about person concerned)
7) NAME GENERATION (persons name)
8) COGNITIVE SYSTEM (additional info)

Question 32

According to Bruce & Young (1986) there are major differences in the processing of _____ and _____?

Answer 32

Familiar and unfamiliar faces

Question 33

What is Duchaine & Nakayama (2006) developmental prosopagnosia?

Answer 33

Faces are recognised by a content specific face processing mechanism

Question 34

What’s capgras syndrome?

Answer 34

Disorder in which person believes loved one has been replaced by an imposter - emotional pathway has been damaged

Question 35

What does Berson (1983) say about capgras syndrome?

Answer 35

Suggested alternative explanation, chronic paranoid schizophrenia

Question 36

List 3 implications of face recognition?

Answer 36

• facial attractiveness relates to lenient court decisions “beautiful but dangerous” (sigall & ostrove, 1975)
• recognising familiar faces over unfamiliar faces (burton et al)
  Vs.
• familiarity hypothesis, unfamiliar faces better remembered if unusual (Bartlett et al)