Perception process of interpreting sensory information the

Perception of everything around us is based upon the fundamental
principles of pattern recognition, which involves simplifying complex sensory
stimuli into patterns that are easier to interpret and distinguish between.
Pattern recognition is a cognitive process which involves matching information
of a stimulus with information previously stored in our memory (DiCarlo et al.,
2012). The recognition of patterns allows us to differentiate between a slice
of pizza and an apple because of the different parts that make up each object,
which are known as geons. A geon is defined as a 3-D object such as spheres, blocks
and arcs among many more that correspond to the simple components used to make up
a complex object (Biederman, 1987). An example of this is viewing an ice cream
cone into its basic geons: a sphere on top of a cone. A geon can be arranged to
form virtually an unlimited number of different types of objects.

The concept of breaking down objects into simpler parts for
recognition was proposed by Irving Biederman in 1987 through the
recognition-by-components (RBC) theory, which was structured around the concepts
of bottom-up processing and feature analysis model of pattern recognition
(Biederman, 1987). Bottom-up processing involves the process of interpreting
sensory information the moment it is presented and then later processing it in
the brain to understand what was perceived (Ochsner et al., 2009). Feature
analysis model is a type of pattern recognition focused around an analytical
approach towards perception by breaking down sensory stimuli into its basic
fundamental parts (Nothdurft, 1992). Similarly,
the RBC theory shows that perception is an analytical process which is heavily
reliant on the ability to detect patterns allowing us to perceive complex
images by breaking them down to a simple arrangement of geons.

It is believed that there are 36 geons or less that
can be arranged in a variety of different ways in order to create any of the
objects we see on a daily basis (Biederman, 1987). Biederman stated that if
speech can be broken down to a number of phonemes, which are units of sound, then
similarly the perception of objects can be broken down to a number of geons
(Biederman, 1987). If 55 phonemes are required to create every word in all
languages then similarly, 36 geons can be used to create all the different
types of objects in the world (Biederman, 1987). An object is defined by two criteria’s,
edges and concavity. Edges allows an individual to maintain the perception of
an image regardless of the orientation the object is being viewed from
(Biederman, 1987). Concavities of an object refers to the area where two or
more edges meet, this allows for the distinguishing of two or more geons
present within an object (Biederman, 1987).

A study was conducted to determine the importance of vertices,
created by two or more edges, compared to midsegments of an image in terms of
the RBC theory by asking participants to identify images with missing vertices
compared to missing midsegments (Koch & Abbey, 1999). It was found that
there were no significant differences between either the missing vertices or
midsegments, illustrating that one is no more important than the other (Koch
& Abbey, 1999). Therefore, it was concluded that vertices are important but
not necessary for object recognition. This study proved that object recognition
is not reliant on just one of the properties of geons, being edges, but rather
it is reliant on both properties, edges and concavity (Koch & Abbey, 1999).

The RBC theory was largely accepted due to the fact
that it allowed recognition of an object regardless of the viewing angle due to
the invariant edge properties of geons such as curvature, symmetry, parallel
lines, co-termination and co-linearity (Biederman, 1987). These properties
simply allowed for the perception and recognition of an object from any angle,
allowing the theory to be more robust and widely accepted. Irving also stated
that the geons used to make up an object are essentially formed by the five invariant
properties of edges (Biederman, 1987).

Irving Biederman conducted an experiment to test the RBC theory by
presenting participants with objects drawn with only two or more of their
components and asked participants to indicate what the object was after a 100
millisecond exposure to it (Biederman, 1987). The results showed that as the
number of components increased the percent error started decreasing, however
90% of participants were able to correctly identify an object with only 3 to 4
components present, when the actual objects originally consisted of six to nine
components (Biederman, 1987). This experiment proved that humans naturally
break down complex objects into distinct geons which can be used to identify
and differentiate between different objects, even when the image is not
complete with all of its geons.

Despite
how promising the RBC theory seems to be, it is still limited in part due to
specific aspects of perception, specifically regarding the identification of
real objects. It was said that when comparing an apple and an orange, although
it is easily distinguishable by humans, it lacks the edges required for the RBC
theory to recognize the objects as two different objects. Irving Biederman
argued the RBC theory explained a certain extent of perception whereas the
perception of objects that appear similar but are different was due to another
mode of perception (Biederman, 1987). Overall, the RBC theory proposed by
Irving Biederman has provided great insight as to how human beings perceive and
break down complex images into simple geons for perception. This theory has not
only further increased our understanding of perception but it has also allowed
for advancements in technology, specifically related to security and artificial
intelligence.

Go Top