W H I T E
P A P E R
TOP 10 MACHINE VISION IMPROVEMENT
OPPORTUNITIES
Applied Manufacturing Technologies
2
Top 10 Machine Vision Improvement Opportunities
As the global manufacturing market continues to get more competitive, it is important to ensure
that your factory is running at a peak level of efficiency. Any downtime due to process related
malfunctions is considered non value-added downtime directly impacting company profitability.
Machine vision is an area that if setup correctly can reduce process inefficiencies. If your facility
uses machine vision as robot guidance or inspection, there is always an area of improvement that
can be investigated. Listed below are the top ten areas that if not setup correctly, may be causing
non value added downtime to your machine vision process.
Here are the top 10 areas to improve vision system efficiency:
1) Lighting Technique - Are you using the correct lighting techniques to illuminate the region
of interest? Backlighting, Bright Field Lighting, Grazing, Low Angle Linear Array, Dark Field,
just to name a few are lighting techniques which are the most critical aspect of machine
vision robustness. Depending on the part surface finish and contour, the correct lighting
technique will enhance flaws or remove image noise which will increase the efficiency and
stability of your system. The intention is to select a lighting technique that will produce the
maximum amount of contrast (Black to White Pixels) for the area of interest in your
inspection. It is also important to point out that the contrast needs to be directly related to
what you are trying to measure or inspect.
2) Lighting - Are you using the correct color of light for your part or application? Frequency is
the number of oscillations per second, whereas wavelength is the distance between two
points in the same position on the wave. Each different color spectrum, UV, Blue, Green,
Yellow, Red, Infrared are all lighting frequencies that have different frequencies and
wavelengths of light. This will determine how the surface of the object and camera will react
when light is introduced. The intention is to use the light frequency that will create the
greatest contrast and eliminate noise in your image. For example, metallic parts can
sometimes be introduced to a system with a light coating of oil or with a slightly oxidized
surface depending on the logistics of how they were stored. In a situation like this it is
Copyright ©2007 Applied Manufacturing Technologie, Inc.
All Rights Reserveds
3
important to use the frequency of light that will reduce the amount of fluctuation that will
occur when both types of these parts are introduced into the inspection system.
3) Filtering - Are you eliminating background or overhead lighting noise and other harsh
environment disturbances with lens filters? By simply placing a filter on the camera lens that
matches the frequency of lighting illuminating the part, ambient lighting disturbances can be
removed.
Copyright ©2007 Applied Manufacturing Technologie, Inc.
All Rights Reserveds
4
4) Lenses - Do you have the correct Field of View (FOV) and Region of Interest (ROI)
including the pixel accuracy needed? The correct focal length lens will determine the size of
the region your machine vision system can see and ultimately all the information that is
collected. Calculating a FOV too large will result in less detail and accuracy, whereas
calculating a FOV too small may result in inspection failure due to the part or object being
out of the camera sight. When calculating the FOV it is important to determine the part or
object maximum ROI and the maximum acceptable error of that region before deciding
which focal length lens is most appropriate for your application. Sometimes this may be
restricted by the working distance or height of the camera to the object, so all these factors
need to be accounted for, before you build your system.
Copyright ©2007 Applied Manufacturing Technologie, Inc.
All Rights Reserveds
5
5) Location - Are the parts or application tolerances too wide to repeatably detect your part?
Having a part that shifts out of the camera field of view can cause system instability. It is
important to have some type of physical fixture that limits the motion of the object or part
of interest. If the part shifts out of the camera view, failures will occur adding to
unnecessary downtime. By providing a rough location of your part this instability can be
eliminated ensuring that your part will be presented to the machine vision system
repeatably each time.
6) Calibration - Is the system calibrated correctly and how do you test that the calibration
was and is in conformance? Having a mastering fixture or calibration routine can ensure
that your system meets the quality standards of your facility.
7) Features and Fiducials – In order to properly inspect an image the identification of a
unique feature that is present in every inspection image can be used as a point of reference
or what we call a fiducial. Fiducials represent a unique feature found in every inspection that
can be used to reference vision tools in your inspection or detect if you have the correct
part present in your image.
Copyright ©2007 Applied Manufacturing Technologie, Inc.
All Rights Reserveds
6
8) Resolution – Resolution determines the repeatability of your system. This allows you to
quantify the size of a pixel to a measurement value. Determining the resolution of your
system is important because it determines how accurate and repeatable your inspection can
be. If you have a system in which the resolution is .5mm/pix and you need to measure a
part +/- .1mm it may be impossible to ever achieve. This needs to be considered especially
on quality measurement inspections and robot guidance. Resolution can also be enhanced
by the power of the software you choose which can allow sub pixel accuracy.
9) Stability – Another important aspect to consider when setting up a machine vision sensor is
the stability of the system. It is important to ensure that the mounting of your camera
system and lights do not move or shift during your process. These items are what your
system is calibrated too. Moving a camera doesn’t mean that the camera can see that it has
moved, it is only as smart as the programmer can make it. Also, when setting up the
equipment it’s wise to place the cameras and lights in areas with little to no vibration or in
areas with little traffic so that the potential for the system to get bumped or moved is
minimized.
10) Testing – In order to ensure that your machine vision system is working properly it is
important to have a system that can be periodically checked to ensure that defect parts are
being captured and rejected by the system. A testing procedure can be built directly into the
system to ensure that the process is easy and efficient. These test parts are referred to as
“rabbit parts”, which can be placed into the system at anytime to verify the systems proper
functionality.
Each of the areas mentioned above are critical aspects of ensuring that machine vision will be a
successful process in your facility. For expert advice and a more in depth explanation of how each
of these areas pertain to your process, please contact the machine vision department at 248-409-
2000 or [Link]
Copyright ©2007 Applied Manufacturing Technologie, Inc.
All Rights Reserveds
