Lecture 3, Object Recognition

Question 1

What is object recognition?

Answer 1

Perception of objects is different for humans and computers.
For humans –> perception of familiar items
For computers –> perception of familiar patterns

Question 2

Why is object recognition difficult?

Answer 2

• Environment contains hundreds of overlapping objects
• Objects have variability, e.g., translation invariance, rotation invariance, size invariance, colour
• Objects can vary in the visual scene, e.g., partial occlusions and presence of other objects
• Intra-class variation -> same object has different forms, e.g., different types of chairs
• Only part of object may be visible
• Viewpoint variation -> may be more difficult to recognise an object from one viewpoint to another

Question 3

What are theories of 2D pattern matching?

Answer 3

Template theories, prototype theories, feature theories, structural descriptors

Question 4

What are template theories?

Answer 4

Mini copy/template in LTM of all known patterns - compare stimuli to templates in memory for one with greatest overlap until a match is found

Question 5

What are some problems with template theories?

Answer 5

• Imperfect matches
• Cannot account for the flexibility of pattern recognition system
• Comparison requires identical orientation, size, position of template to stimuli

Question 6

What are prototype theories?

Answer 6

Modification of template matching (flexible templates) - possesses the average of each individual characteristic. No match is perfect –> criterion is missing

Question 7

Is there any supporting evidence for prototype theories?

Answer 7

Documented by Franks and Bransford:
–> Presented objects based on prototypes
–> Prototype not shown
–> Ppts confident they had seen prototype
–> Suggests evidence of prototype
HOWEVER, difficult to conclude how you would come up with a prototype

Question 8

What are feature theories?

Answer 8

Pattern consists a set of features or attributes, e.g., letter A = 2 straight lines and connecting bar. However, also need to know the relationship between features. e.g., / \ - = A?

Question 9

What are structural descriptions?

Answer 9

Describe the nature of the components and the structural arrangement of these parts. Composition of object and how they are related together. e.g., Capital letter T = 2 parts; 1 horizontal, 1 vertical; vertical support horizontal; vertical bisects horizontal.

Question 10

What is 3D object recognition?

Answer 10

Must interpret input to the visual system as coherent structures, segregated from one another and from background. Must be processed to give a description which can then be matched to the descriptors of visual objects stored in memory.

Question 11

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

Answer 11

Objects are comprised of cylinders; must specify relationship between cylinders (structural description). Expressed structural relationships by a hierarchical organisation of cylinders. Each cylinder has an axis and way in which others are joined are expressed as coordinates.

Question 12

What are the limitations of Marr and Nishihara’s theory of 3D object recognition?

Answer 12

–> Difficult to think about how to break down all objects into a series of cylinders
–> May work better for biological entities

Question 13

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

Answer 13

Provided an alternative to Marr & Nishihara’s theory.
- Objects comprised of basic shapes
- GEONS -> Geometrical ions
- Approx 36 different shapes
- Viewpoint invariant theory
- Relationship between geons can be described structurally

Question 14

What are some examples of the structural relationships set out by Biederman?

Answer 14

Relative size, verticality, centring, relative size of surfaces at join.

Question 15

What did Biederman believe concave parts of objects were helpful for?

Answer 15

Segmenting visual image into parts

Question 16

Biederman specified GEONS in terms of “non-accidental” properties, what were they?

Answer 16

• Curvature: points on a curve
• Parallel: sets of points in parallel
• Co-termination: edges terminating in a common point
• Symmetry: vs. asymmetry
• Co-linearity: points in a straight line

Question 17

What does “non-accidental” mean?

Answer 17

Regularities in the visual image thought to reflect regularities in the world.
2D symmetry in the visual image indicates symmetry in 3D object -> present in both 2D & 3D views

Question 18

What did Biederman say about form degradation?

Answer 18

It should disrupt the basis for identifying geons; make object more difficult to recognise; deletion of component affects matching stage, reducing the number of components to match to.

Question 19

Midsegment deletion makes it more difficult to what?

Answer 19

Determine components

Question 20

Describe Biederman’s study that documented effects of degradation?

Answer 20

-> Deleted edges at points where easily reinstated or difficult to determine
-> 25, 45, or 65% of contours removed
-> Slow & inaccurate at “non-recognisable” but relatively good at “recognisable”
-> At brief exposures -> partial objects are better recognised
-> At longer exposures -> midsegment deletion led to less errors

Question 21

What did Vogels, Biederman, Bar & Lorincz, 2001, find in monkeys sensitive to geons?

Answer 21

• Cortical neurons.
  -> Assessed response of individual neurons in the inferior temporal cortex to change in geon or change in size of object.
  -> Some neurons responded more to geon changes, providing support for geons

Question 22

What are the evaluations of Biederman’s model?

Answer 22

• Flexible and comprehensive system for describing objects, but why 36 geons?
• Experimental results consistent with model but doesn’t provide critical test
• Doesn’t explain how description are matched to those stored

Question 23

What are the advantages of Biederman’s theory?

Answer 23

• Recognises importance of the arrangement of the parts
• Parsimonious: small set of primitive shape

Question 24

What are the disadvantages of Biederman’s theory?

Answer 24

• Structure is not always key to recognition, e.g., Peach vs. Nectarine -> texture is necessary
  -> Within category discrimination
  -> De-emphasise the role played by context in object recognition (affects later stages of object recognition)
  -> Simplifies the contribution of viewpoint-dependence

Question 25

What do viewpoint-dependent theories assume?

Answer 25

Changes in viewpoint reduce the speed and/or accuracy of object recognition. Object representations are collections of views that depicit the appearance of objects from specific viewpoints.

Question 26

What is viewpoint dependent more important for?

Answer 26

Within-category discrimination

Question 27

What does evidence suggest concerning viewpoint invariant mechanisms vs viewpoint dependent mechanisms?

Answer 27

Viewpoint dependent = complex within category decisions
Viewpoint invariant = easy categorical decisions

Question 28

What is Humphrey’s Cascade Model?

Answer 28

Structural, semantic and name stages - both within and between stages.
-> Makes different predictions about how subjects will perform in object naming task.
–> Problems at one stage will have a knock on effect.

e.g., Patient JB - naming visually confusable words (birds, animals) had knock-on effects, making it difficult to identify their category

Question 29

What is agnosia?

Answer 29

Failure of knowledge or recognition

Question 30

What is visual agnosia?

Answer 30

-> Feature processing and memory remain intact
–> Recognition deficits are limited to visual modality
—> Alertness, attention, intelligence and language are all unaffected
—-> Other sensory modalities (touch, smell) may substitute for vision in allowing objects to be recognised

Question 31

What is apperceptive agnosia?

Answer 31

Problems with early processing (shape extraction)
-> Perceptual deficit, affects visual representations directly
–> Components of visual percept are picked up, but can’t be integrated
—> Effects may be graded
—-> Often affected: unusual views of objects

Question 32

What is associative agnosia?

Answer 32

Problems with later processing (recognition). Visual representations are intact, but cannot be accessed or used in recognition - lack of information about the percept. “Normal percepts stripped of their meaning.”