15. object recognition Flashcards
2 approaches for object recognition?
- recognition by components
- viewpoint-specific
Recognition by components?
- use geons to assemble and recognize a whole object
- A model of object recognition that proposes that recognizing an object depends on first identifying the object’s basic 3-D shapes and how they fit together.
Evidence for recog. by componenets?
- we can rec. an object even if we only have some of its geons
- its really difficult to identify an object if you can’t identify geons
Limitations of recog. by components?
- it achieves invariance… but its often too abstract
- ALL briefcases would look the same, couldn’t DISTINGUISH between them
- the model is too extreme
viewpoint-specific meaning?
- objects are recognized based on view-specific representations stored in memory
- ie. multiple representations, for each possible view, are stored at the same time
Evidence for viewpoint-specific?
- artificial objects are recognized more quickly when seen from a familiar viewpoint
Limitations for viewpoint-specific?
- do we have enough room in our brains to store all the different representations we would need?? (no)
Grandmother cell?
- truly invariant –> responds to an image of a toaster and the concept (word) toaster
- can’t be used to guide action
- debated, cuz it would require enormous amounts of neurons for all objects and concepts
- A neuron that responds to a particular object at a conceptual level, firing in response to the object itself, a photo of it, its printed name, and so on.
Top-down meaning? What kind of information?
cognitive influence on perception
- perceiver’s goals
- attention
- prior knowledge
- expectations ab what objects are likely to occur in the current scene
Bottom-up meaning?
based only on stimulus
How does the “gist” affect object recognition? Vice versa?
- We’re much worse at identifying objects when they’re at an atypical location in the scene or in an inappropriate scene
- We’re much better at identifying the correct scene (background) if the object and scene are correct
How are recognition of the gist and the object related? —> When?? What helps what?
- we likely process both at the same time
- after identifying “gist” –> top down expectations of what objects are most likely to be in certain scenes help with object recognition
Bayesian approach?
- visual system uses 2 probabilities to infer the scene from the retinal image:
1. prior probability of all scenes
2. for each scene, probability that it produced the current retinal image - use of mathematical probabilities to describe the process of perceptual inference
Spatial frequency def? What does high vs low look like?
- describes periodic distribution of light and dark in an image
- low: fuzzy, big blobs of color
- high: only fine details, little/no color
Units for spatial frequency?
- Cycles per degree
- more cycles = higher sp. frq.
Degrees of visual angle?
- angle measure (in degrees)between the rays on either side of an object
- specifies the size of an object on the retina
–> 1 to 1 correspondence
Spatial frequency channels? Perception of sp. frq?
- neural mechanisms that are sensitive to only a narrow range of spatial frequencies
- neurons / general perception is NOT equally sensitive to all spatial frequencies!
Contrast sensitivity function shows? (axis?)
Axes:
x: relative sensitivity
y: sp. frq. (cycles per degree)
- we are most sensitive to INTERMEDIATE spatial frequencies
How does moving closer/further affect sp. frq?
Closer –> REDUCES sp. frq
–> closer usually helps
Further –> INCREASES it
You’re looking at something with high sp. frq. To make it easier to see, should you move closer or farther?
CLOSER
You’re looking at something with low sp. frq. To make it easier to see, should you move closer or farther?
FARTHER
You’re looking at an object. When you move closer to it, it becomes harder to see. Does the object have high or low sp. frq.?
LOW
