B51.CH4.docx

33 views2 pages
26 Apr 2012
School
Department
Course
Page:
of 2
Chapter 4
- Middle (midlevel) vision: a loosely defined stage of visual processing that comes after basic
features have been extracted from the image (early vision) and before object recognition and
scene understanding (high-level vision)
Middle Vision
- Goal of middle vision is to organize the elements of a visual scene into groups that we can then
recognize as objects
- Illusory contours: a contour that is perceived, even though nothing changes from one side of the
contour to the other in the image
- Structuralists: argued that perceptions are the sum of atoms of sensation bits of colour,
orientation etc; perception is built up of the local sensations the way a crystal might be built up of
an array of atoms
Structuralism: a school thought believing that complex objects or perceptions could be
understood by analysis of the components
- Gestalt: “form”, school of thought stressing that the perceptual whole could be greater than the
apparent sum of the parts
Gestalt Grouping Rules: a set of rules describing which elements in an image will appear
to group together; guide the retinal visual system in its interpretation of the raw retinal
image
The Principle of Good Continuation: a gestalt grouping rule stating that two elements will
tend to group together if they seem to lie on the same contour
“all else being equal”- perceptual committees a consensus view on a single
interpretation of the visual scene
Texture Segmentation: carving an image into regions of common texture properties
Similarity: the tendency of two features to group together will increase as the similarity
between them increases
Proximity: the tendency of two features to group together will increase as the distance
between them decreases
Parallelism: a rule for figure-ground assignment stating that parallel contours are likely to
belong to the same figure
Symmetry: a rule for figure-ground assignment stating that symmetrical regions are more
likely to be seen as a figure
Common Region: grouping rule stating that two features will tend to group together if
they appear to be part of the same larger region
Connectedness: grouping rule stating that two items will tend to group together if they are
connected
- Ambiguous Figure: a visual stimulus that gives rise to two or more interpretations of its identity
or structure ex. Necker Cube, Duck-Rabbit
- Accidental Viewpoint: a viewing position that produces some regularity in the visual image that
is not present in the world (ex. Shades of two independent objects lining up perfectly)
Another set of assumptions made by the visual system involves an implicit understanding
of some aspects of the physics of the world
- Figure-Ground Assignment: the process of determining that some regions of an image belong to a
foreground object (figure) and other regions are part of the background (ground) ex. Vase/Face
- Principles involved in the assignment of Figure or Ground
a) Surroundedness: if one region is entirely surrounded by another, it is likely that the
surrounded region is the figure
b) Size: the smaller region is likely o be the figure
c) Symmetry: a symmetrical region is more likely to be seen as figure
d) Parallelism: regions with parallel contours are more likely to be seen as figure
e) Extremal Edges: see figure 4.21 p. 89
f) Relative Motion: how surface details move relative to an edge can also determine which
portion of a display is the foreground figure and which is the background
- Reliability: the degree to which two line segments appear to be part of the same contour
- Heuristic: a mental shortcut
- Nonaccidental Feature: a feature of an object that is not dependent on the exact (or accidental)
viewing position of the observer