Machine vision is not a subset of:. Computer Science Image Processing Pattern Recognition Artificial Intelligence (whatever this is!) However, tools and concepts from these areas are often applied to vision applications. Machine vision is.
However, tools and concepts from these areas are often applied to vision applications.
A Simple 1-D Model For Illumination
Incident light reaching a linear sensor can be expressed as:
In which I[n] is the light reaching the nth pixel, L[n] is the background illumination and s[n] is the value of reflection or transmission of the object being observed which can range between 0 and 1.
The sensor converts the light into an electrical signal v[n]
v[n] = b[n]s[n]
in which b[n] is proportional to I0[n].
yhp[n] = b[n]s[n] ‑ b[n] = b[n](s[n] - 1)
High-Pass Filtering Homomorphic Filtering
Original Image Log Transformed
Consider a FIR filter that will remove the DC component over
Assuming that all pixels have gray-scale value , then
From this, it can be inferred that
Now, since v[n] = s[n]b[n]
For slowly varying illumination, b[k] is assumed to be
the constant over the filter extent so y[n] does not
depend on illumination:
I0[j,n] = It[j]Is[n]
v[j,n] = It[j]b[n]s[j,n]
d[j,n] = log(It[j]b[n]s[j,n]) = log(It[j]) + log(b[n]s[j,n])
logIt[j] is constant for all pixels in region R since it only varies as a function of the sample number.
A constant kR can be defined as
A normalized image in which compensation for the short-term variations are provided follows:
dn[j,n] = logIt[j] + log(b[n]s[j,n] - a[j]
= logIt[j] + log(b[n]s[j,n] - log(It[j]) - kR
=log(b[n]s[j,n]) - kR
the amount of processing required is relatively small.
The region R need only be large enough to minimize errors due to camera signal noise.
The image normalization operation simply requires that a constant value be added to each pixel