Neurobiological Background - Hierarchical Neural Networks for Image Interpretation - page 17

2. Neurobiological Background
Learning from nature is a principle that has inspired many technical developments.
There is even a field of science concerned with this issue: bionics. Many problems
that arise in technical applications have already been solved by biological systems
because evolution has had millions of years to search for a solution. Understanding
nature's approach allows us to apply the same principles for the solution of technical
problems.
One striking example is the 'lotus effect', studied by Barthlott and Nein-
huis [17]. Grasping the mechanisms, active at the microscopic interface between
plant surfaces, water drops, and dirt particles, led to the development of self-
cleaning surfaces. Similarly, the design of the first airplanes was inspired by the
flight of birds and even today, though aircraft do not resemble birds, the study of
bird wings has lead to improvements in the aerodynamics of planes. For example,
birds reduce turbulence at their wing-tips using spread feathers. Multi-winglets and
split-wing loops are applications of this principle. Another example are eddy-flaps
which prevent sudden drops in lift generation during stall. They allow controlled
flight even in situations where conventional wings would fail.
In the same vein, the study of the human visual system is a motivation for de-
veloping technical solutions for the rapid and robust interpretation of visual infor-
mation. Marr [153] was among the first to realize the need to consider biological
mechanisms when developing computer vision systems. This chapter summarizes
some results of neurobiological research on vision to give the reader an idea about
how the human visual system achieves its astonishing performance.
The importance of visual processing is evident from the fact that about one third
of the human cortex is involved in visual tasks. Since most of this processing hap-
pens subconsciously and without perceived effort, most of us are not aware of the
difficulties inherent to the task of interpreting visual stimuli in order to extract vital
information from the world.
The human visual system can be described at different levels of abstraction. In
the following, I adopt a top-down approach, while focusing on the aspects most rel-
evant for the remainder of the thesis. I will first describe the visual pathways and
then cover the organization of feature maps, computation in layers, neurons as pro-
cessing elements, and synapses that mediate the communication between neurons.
A more comprehensive description of the visual system can be found in the topic
edited by Kandel, Schwartz, and Jessel [117] and in other works.