Class 2, Lecture 3, Chapter 3: Recognizing Objects
How do we perceive and recognize objects?
Form perception is the process through which the basic shape and size of an object
Object recognition is the process through which the object is identified.
Object recognition begins with the detection of simple visual features.
However, our perception of the visual world goes “beyond the information given”
o All the demonstrations of optical illusions go to how that cognition interacts
with perception, our assumptions and expectations and life experiences
influence what we see
An early twentieth-century movement known as Gestalt psychology captured this
idea as “the whole is different from the sum of its parts.”
The Necker Cube is an example of perception going “beyond the information given.”
o Two different perceptions of depth are possible, given the lines on the page.
In the Face-Vase figure, two interpretations are possible, each based on a different
o This again shows that perception goes “beyond the information given.”
These examples might suggest that perception proceeds in two stages:
o One where visual features are processed
o And a later stage in which perception goes “beyond the information given.”
However, this view presumes serial processing, not the parallel processing that
characterizes the visual system.
Our interpretation of the visual input influences how basic visual features are
In this image, it is only when the white parts of the figure are treated as figure, and
not ground, that the features of letters are analyzed.
o In this image, the word “perception” is recognized even though most of the
features of the component letters are absent from the stimulus.
These examples illustrate that the brain areas that analyze basic visual features and
the brain areas that analyze large scale form are interactive, each sending information
to the other
This again is an example of parallel processing
o What this means is that what we see is not just determined by the stimuli in
front of our eyes, but also the brain’s interpretation of that stimulus.
o The perceptual system operates as if it were generating hypotheses about what
objects are being perceived, given the available data.
The visual system prefers the simplest explanation possible, avoiding interpretations
that involve coincidences.
This figure is interpreted as two crossed lines, and not two V shapes precisely
Now let’s turn from form perception, the process through which the basic shape and
size of an object are seen,
And discuss object recognition, the process through which the object is identified.
A first consideration about object recognition is that we can recognize objects when
information is incomplete.
E.g., a cat behind a tree is recognized even if only the head and one paw can be seen.
The context in which objects are viewed also can have a large effect.
o It is hard to see the item that is out of context in a scene.
Recognition might begin with the input pattern’s features – the small elements out of
which more complicated patterns are composed
Not that here the features are not those of the raw input, but rather those that result
from more organized perception of form
The feature of the triangles that are missing ALL of the characteristics are inferred,
however, in the visual system’s organized perception of form.
Advantages of a feature-based system:
o Features could serve as building blocks, allowing a single object-recognition
system to deal with a variety of targets.
There can be variations in the physical characteristics as long as the
frame for the object is there. Example: Varying looks of chairs yet we
still know that they are chairs even if we have never seen them before. Consistent on how we recognize novel examples from categories we
have never seen before.
o Focusing on features might allow us to concentrate on