what is the process of object recognition
detecting objects in an image and matching those objects with existing, stored representations of what those objects are
what is the inverse projection problem
task of determining the object responsible for a particular image on the retina
define viewpoint invariance
ability to recognize an object seen from different viewpoints
what are the three problems machines face when perceiving objects
define perceptual organization
process by which elements in a person’s visual field become perceptually grouped and segregated to create a perception
what are the two components involved in perceptual organization?
define structuralism
sensations combine to create complex perceptions
what is apparent movement
although movement is perceived, nothing is actually moving
what are the two conclusions drawn from the phenomenon of apparent movement
what are illusory contours
illusion that there are physical edges present when there are none
what are gestalt principles of perceptual organization
what is reversible figure-ground
when the front and the background can be alternated
what are some properties of figure and ground
name the figural cues that determine figure-ground
describe the gestalt ideas about the role of meaning and past experience in determining figure-ground segregation
describe gibson and peterson’s experiment that showed that meaning can play a role in figure-ground segregation
define the recognition by components theory (RBC)
objects are comprised of individual geometric components called geons, and we recognize objects based on the arrangement of those geons
According to Biederman, what are examples of geons and how many are there
three-dimensional shapes like pyramids, cubes and cylinders
- 36 different geons that can be assembled to form different objects
why does the RBC theory account for viewpoint invariance
because whether you see an object from the side or from the front, it is still comprised of the same geons, so it should still be recognized as the same object
what are 3 aspects that the RBC theory could not explain
what is the definition of a scene
view of a real-world environment that contains
1. background elements
2. multiple objects that are organized in a meaningful way relative to each other and to the background
define what the gist of a scene is
being able to identify important properties of most scenes after viewing them for only a fraction of a second
what is the phenomenon called persistence of vision
the perception of a visual stimulus continues for about 250 ms after the stimulus is extinguished
how can persistence of vision be eliminated
by presenting a masking stimulus, a random pattern that covers the original stimulus