Lecture 3 - Object Recognition

Question 1

What’s the diff for humans + computers perceiving objects?

Answer 1

H: perception of familiar items
C: perception of familiar patterns

Question 2

Why is object recognition difficult?

Answer 2

Environment has hundreds of overlapping objects but perceptual experience structure + coherent (we use/name)

Apparent size/shape of object doesn’t change despite large variation in retinal image

Question 3

What are 4 types of variability in recognition?

Answer 3

1. Translation invariance (diff locations in field of view)
2. Rotation invariance
3. Size invariance
4. Colour invariance

Question 4

Other factors in object recognition?

Answer 4

Partial occlusion, presence of other objects

Intra-class variation (variety of chairs that don’t look the same)

Viewpoint variation

Question 5

4 types of theories of 2D pattern matching?

Answer 5

1. Template
2. Prototype
3. Feature
4. Structural

Question 6

What are template theories?

Answer 6

Mini-copy/template in LTM of all known patterns, multiple templates in memory then compare stimuli to templates to find greatest overlap

Question 7

Problem with template theories?

Answer 7

Normalisation? Numerous templates? (examples: barcodes, fingerprints)

Problem: imperfect matches, flexibility of pattern recognition system, comparison requires identical orientation/size/position to stimuli

Question 8

What are prototype theories?

Answer 8

Modification of template matching (flexible templates), possesses average of each individual characteristic, no match perfect, criterion for matching is needed - Franks/Bransford study

Question 9

What are feature theories?

Answer 9

Pattern consists of set of features/attributes (A = 2 straight lines + connecting bar) –> but also need to know relationship between features? / \ = A??

Question 10

What are structural descriptions?

Answer 10

Describe nature of components of configuration + structural arrangement of these parts

Question 11

How is 3D object recognition more difficult?

Answer 11

First interpret input to visual system as coherent structures, segregated from one another + background –> processed to give description which can be matched to description in memory

Question 12

What did Marr + Nishihara study?

Answer 12

Objects made of cylinders, must specify relationship between cylinders to make structural description (hierarchical organisation of cylinders)

Question 13

What did Biederman do?

Answer 13

Alternative to Marr + Nishihara – Recognition by components theory: objects composed of basic shapes (36 GEONS – geometrical ions) viewpoint invariant theory, use structural relations between the parts

Question 14

How are geons specified?

Answer 14

Non-accidental properties:
Curvature (points on curve), parallel (set of points in parallel), co-termination (edges terminating in common point), symmetry (vs asymmetry), co-linearity (points in straight line)

Question 15

What did Biederman test (forms of degredation)

Answer 15

Forms of degradation which disrupt basis for identifying geons should make objects more diff to recognise – deleted edges at points that were easily reinstated/diff to determine

Question 16

How did deletion of components affect recognition?

Answer 16

Slow/inaccurate at non-recognisable but relatively good at recognisable

Deletion of component affects matching stage, midsegment deletion makes it more diff to determine components –> at brief exposure partial objects better recognised but longer midsegment deletion led to less errors

Question 17

Evaluation of Biederman’s Geons?

Answer 17

Good: recognises importance of arrangement of parts, parsimonious (small set of primitive shapes)

Bad: structure not always key to recognition, which geons?, within category discrimination, de-emphasise role played by context, simplifies contribution of viewpoint-dependence, experiment consistent but not critical test

Question 18

What is viewpoint dependent theory?

Answer 18

Assume changes in viewpoint reduce speed/accuracy of object recognition

Object representations collections of views that depict appearance of objects form specific viewpoints

Question 19

Under what circumstances is viewpoint invariant/dependent theories important?

Answer 19

Dependent: complex within category
Invariant: easy categorical

Question 20

What is Humphreys model of recognition?

Answer 20

Object –> structural description –> semantic representation –> name representation –> name

Question 21

Problem with object recognition theories?

Answer 21

Oversimplification, later processes might start before earlier ones completed

Support from patients w/ object recog diffs (associative agnosia) - patient HJA, JB
JB - naming visually confusing objects had knock on effects, diff to identify category

Question 22

Alternative to Humphreys mode?

Answer 22

Cascade model - structual/semantic/name stages interact within/between stages

Question 23

What are agnosias?

Answer 23

Failure of knowledge/recognition

Visual agnosia: feature processing/memroy remain intact, recognition defivits limited to visual modality

Touch/smell may substitute in recognition

Question 24

What is apperceptive agnosia?

Answer 24

Problems with early processing (shape extraction)

Perceptual deficit affects visual representations directly, components of visual percept picked up but can’t be integrated –> unusual views of objects

Question 25

What is associative agnosia?

Answer 25

Problems w/ later processing (recognition), visual representation intact but can’t be accessed/used in recognition, lack of info about percept