Week 3 Lecture 3 - object recognition Flashcards
What is object recognition?
- perception of objects is different for humans and computers
for humans –> perception of familiar items
for computers –> perception of familiar patterns
Why is object recognition difficult?
- 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 1 viewpoint compared to another
What are the theories of 2D pattern matching?
- template theories
- prototype theories
- feature theories
- structural descriptions
What are template theories?
- 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
What are some problems with template theories?
- imperfect matches
- cannot account for the flexibility of pattern recognition system
- comparison requires identical orientation, size, position of template to stimuli
What are prototype theories?
- modification of template matching (flexible templates)
- possesses the average of each individual characteristic
- no match is perfect –> criterion is needed
What is some supporting evidence for prototype theories?
Franks and Bransford
- presented objects based on prototypes
- prototype not shown
- ppts confident they had seen prototype
- suggests existence of prototype
however difficult to conclude how you would come up with a prototype
What are feature theories?
- pattern consists of a set of features or attributes
- e.g., letter A = 2 straight lines and connecting bar
What is an issue with feature theories?
- also need to know the relationship between features
- e.g., / \ - = A?
What are structural descriptions?
- 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
What is 3D object recognition?
- 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 descriptions of visual objects stored in memory
What was Marr and Nishihara’s theory of 3D object recognition?
- objects are comprised of cylinders
- must specify relationship between cylinders (structural description)
- expressed structural relations by a hierarchal organisation of cylinders
- each cylinder has an axis and way in which other are joined are expressed as coordinates
What is an issue with Marr and Nishihara’s theory of 3D object recognition?
difficult to think about how to break down ALL objects into a series of cylinders
may work better for biological entities
What was Biederman’s theory of 3D object recognition?
- provided alternative to Marr and Nishihara’s theory of 3D object recognition
Recognition by components theory:
- objects comprised of basic shapes
- GEONS –> geometrical ions
- approx 36 different shapes
- viewpoint invariant theory
- relationship between geons can be described structurally
What are some examples of the structural relationships set out by Biederman
- relative size
- verticality
- centring
- relative size of surfaces at join
What did Biederman believe the concave parts of objects were helpful in?
segmenting visual image into parts
Biederman specified Geons in terms of “non-accidental” properties
What were they?
- 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
What does “non-accidental” mean?
regularities in the visual image thought to reflect actual regularities in the world
2D symmetry in the visual image indicates symmetry in 3D object
Present in both 2D and 3D views
According to Biederman, what should form of degradation do?
- disrupt the basis for identifying geons
- make object more difficult to recognise
- deletion of component affects matching stage –> reducing the number off components to match to
- midsegment deletion makes it more difficult to determine components
What study did Biederman conduct to show the effects of degradation?
- deleted edges at points where easily reinstated or difficult to determine
- 25, 45 or 65 % of contours removed
- slow and inaccurate at “non-recognisable” but relatively good at “recognisable”
- at brief exposures –> partial objects better recognised
- at longer exposures –> midsegment deletion led to less errors
What is some further support of Biederman’s viewpoint invariant theory?
- Vogels, Biederman, Bar & Lorincz (2001) found some cortical neurons in monkeys sensitive to geons.
- 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.
What is an evaluation of Biederman’s model?
- flexible & 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
What are some advantages and disadvantages of Biederman’s theory?
advantages:
- Recognizes the importance of the arrangement of the parts
- Parsimonious: Small set of primitive shapes
disadvantages
- Structure is not always key to recognition: Peach vs. Nectarine –> texture necessary here
- Within category discrimination (which chair?)
- De-emphasise the role played by context in object recognition (affects later stages of object recognition)
- Simplifies the contribution of viewpoint-dependence
What do viewpoint dependent theories assume?
assume changes in viewpoint reduce the speed and / or accuracy of object recognition
What are viewpoint dependent theories?
object representations are collections of views that depict the appearance of objects from specific viewpoints
What is viewpoint dependent more important for?
within category discrimination
What does evidence suggest about viewpoint invariant and dependent mechanisms?
Evidence suggests that viewpoint invariant mechanisms used sometimes in object recognition whereas viewpoint dependent mechanisms used at other times
What are the main differences in use between viewpoint dependent and viewpoint invariant?
Viewpoint dependent = complex within category decisions
Viewpoint invariant = easy categorical decisions
What is Humphrey’s cascade model?
- structural, semantic and name stages interact.
-both within and between stages.
Makes different predictions about how subjects will perform in object naming task. Problems at one stage will have ‘knock on’ effect….
e.g. Patient JB. Naming visually confusable objects (birds, animals) had knock on effects, making it more difficult to identify their category.
What is agnosia?
failure of knowledge or recognition
What is visual agnosia?
- feature processing and memory remain intact
- recognition deficits are limited to the visual modality
- Alertness, attention, intelligence and language are unaffected
Other sensory modalities (touch, smell) may substitute for vision in allowing objects to be recognized
What is apperceptive agnosia?
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
What is associative agnosia?
- 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”
