Application Note | Case Study | Technology Primer | White Paper

Basics of Understanding
This can be a part of the inspection process itself (e.g.
Machine Vision checking a measurement or identifying whether a character
string is printed correctly) or through some other input
needed for control (e.g. robot control or type verification).
An Introduction to Machine Vision
The machine vision system can include almost any number
Machine vision (also called “industrial vision” or “vision
of cameras, all capturing, interpreting and signaling
systems”) is the use of digital sensors (wrapped in
individually to a central control system according to a pre-
cameras with specialized optics) that are connected to
determined tolerance or requirement.
processing hardware and software algorithms to visually
inspect…pretty much anything. Machine vision is a
This makes it easy to automate complex multi-stage visual
true multi-disciplinary field, encompassing computer
inspection tasks, or simply perform simple inspections
science, optics, mechanical engineering, and industrial
at speed and scale. These kinds of applications include
automation. While historically the tools of machine vision
positioning, identification, verification, measurement, and
were focused on manufacturing, that’s quickly changing,
flaw detection. Machine vision system has driven ever
spreading into medical applications, research, and even
higher standards in manufacturing— improved product
movie making.
quality, higher yields and lower production costs. The
net result is greater productivity and improved customer
A machine vision system combines image capture and satisfaction through the consistent delivery of quality
processing systems (computer hardware and software) products.
with digital input/output devices (cameras) and computer
networks (to store and share the image data) to drive
real-time quality control systems, or to direct equipment,
such as manufacturing robots. This is slightly different
from “computer vision,” which is primarily about image
processing. Instead, machine vision systems are built for
visual inspection and control under demanding industrial
applications that require high-speed, high-magnification,
24-hour operation, and/or repeatable measurements.

Doing a Thankless Job Really Well

No machine beats human vision for versatility, but
other human weaknesses limit their productivity in a
manufacturing environment. Because these kinds of jobs
are “no fun.” Boredom, distraction, and fatigue all typically No machine beats human vision for versatility, but other
human weaknesses limit their productivity in a manufacturing
degrade human performance in vision-related factory
environment. Because these kinds of jobs are “no fun.”
tasks like inspection, which require high speeds, constant
operation and a lot of monotony.
Where Do You Want to Go Next?
Factory automation utilizing a machine vision system Because machine vision systems are used literally
in such tasks, then, offers many benefits. Machine everywhere—in factories, on the road, and in space—the
vision systems can perform repetitive tasks faster and pieces they are built from need to be standardized but
more accurately, with greater consistency over time customizable. In general, each component of a machine
than humans. They can reduce labor costs, increase vision system does one thing. This makes it easier to
production yields, and eliminate costly errors associated swap parts to add a new capability or level of performance
with incomplete or incorrect assembly. They can without replacing parts unnecessarily. It also makes it
help automatically identify and correct manufacturing simple to replace a part that has failed. Cameras have
problems on-line by forming part of the factory control gone from the weakest link in the chain to the pixel-
network.

continued >
1 Property of Teledyne DALSA. Not for publication or reproduction without permission.

Copyright © 2014 Teledyne DALSA. All Rights Reserved.

 Application Note | Case Study | Technology Primer | White Paper

pushing drivers of innovation in the rest of the system. This

is in contrast to a consumer-level digital camera or even
digital film camera, which will record light, but also perform
different degrees of processing to improve image quality
or reduce file sizes as well as record out to a transferrable
medium.

Elements of Your Awesome Vision System

A typical machine vision system will be part of an
automated production process consisting of the following
components: Figure 1: A basic machine vision system. The target is lit as
it moves across the camera’s field of view, and the data is
Camera: Systems will have one or more digital cameras transferred to the vision processing system.
that record color, monochrome, or wide-spectrum images.
Just like consumer cameras, the optics/lenses attached While the additional features and operational requirements
deliver a specific field of view and available light. To pick depend on the application, all machine vision systems
the proper lens you will first need to know the field-of-view share some fundamental attributes and behaviors.
(FOV) and the working distance. The FOV is the size of Systems all have a need to image or inspect a scene or
the area you want to capture. The working distance is object, operating on a continuous basis at the fastest
approximately the distance from the front of the camera to practical speed.
the part being inspected. A more exact definition takes into
account the structure of the lens.

Trigger: This component makes sure that specific action

takes place in response to something the camera sees. A
synchronizing sensor for part detection (often an optical
or magnetic sensor) to trigger image acquisition and
processing and some form of actuators to sort, route or
reject defective parts

Image Processor: A computer program (normally running

on a version of Microsoft Windows) to process images,
detect, measure, compare etc. in order to confirm a quality Figure 2: An inspection system that not only visually inspects the
criteria has been met or to provide type verification or target, but feeds the acquisition system to react based on the
scanned information. Objects that don’t meet specifications are
robot control to another control system. rejected from the assembly line.

Cables: Input/output hardware (e.g. digital I/O) or The essential elements of an inspection system, shown in
communication links (e.g. Ethernet, USB, Firewire, Figure 2, include a delivery vehicle, the vision system, the
CameraLink, etc.) to report results and to automatically response system, and sensors to trigger image capture
reject components. and system response. The delivery vehicle positions the
object for inspection. The vision system, which includes
Building Your Own System camera, optics, lighting, and image processor, captures
Any machine vision system consists of a few critical and processes the object image to determine a pass/fail
components. The image sensor/ camera captures light response. The response system takes the required action
and converts it into an electrical signal that computers as well as communicating results to operators or other
can understand and sends it to a processing engine that systems. The sensor triggers a response, identifying when
renders and communicates the result to a computer that the object is positioned properly for the system to perform
can do something with it. their tasks.

continued >
2 Property of Teledyne DALSA. Not for publication or reproduction without permission.

Copyright © 2014 Teledyne DALSA. All Rights Reserved.

 Application Note | Case Study | Technology Primer | White Paper

The first, and arguably most important, step in developing

an inspection system is positioning or “staging. After
all, no amount of processing can retrieve information
that a sensor didn’t capture at the scene. This is the
determination of how a subject will be situated in front
of the camera for imaging. Figuring out how objects will
be delivered to the camera and sensor can also be the
hardest part of machine vision design. The delivery choice Figure 4: Full motion picture machine vision. Instead of the target
moving at high speed on an assembly line, the front end of the
will frame all the remaining system choices, including
vision system is in motion.
camera, lighting, sensors, and response systems.
And it seems like the camera can go almost anywhere.
Let’s look at a few extreme examples. Instead of objects
The system in Figure 4, works for filming movie stunts,
being delivered via conveyer belt in a tidy and predictable
reversing the motion relationship that typical vision
fashion, they could run or even fall in.
assumes: here the camera the thing that is moving. That
which is being filmed, namely the motorcycle and rider,
does not move in relationship to the camera. The other
subject being recorded, the scenery is fixed. It’s the
camera that is moving at 240km/hour.

Getting Better All the Time

It’s not just what’s possible—it’s what you do with it.
Strong industry innovation and competition have driven
dramatic improvements in what cameras, processing, and
automation can do. Visual inspection makes it possible to
precisely guide robots and other machinery to create more
adaptable manufacturing processes. Custom products
Figure 3: The conventions of an inspection system get turned on
and more variable production environments are possible
their head. Multipe cameras are ringed around the target. The when machines can see as well as build and much of this
multiple visual information feeds are joined together to build a is taking place on line, making for a more efficient and
more complete picture - whether it’s a winning touchdown or a faster inspection and eliminating waste or scrap material
secret spy skydiving.
as they run.

In the case of systems built by Replay Technologies for With a never-ending thirst for improved quality and the
their stadium systems, the target is in the middle. It can availability of higher resolution cameras with faster and
be used to capture an entire football or basketball game. more efficient processing power, increasing bandwidth,
or it could be a James Bond skydiving scene in Quantum and access to lower cost cabling and storage, there
of Solace. In the latter, the cameras were in a ring around truly is no limit to where one might find what started as
a wind tunnel to ensure that action was captured from machine vision. The sky (and the universe) truly is just the
multiple angles. beginning.

www.teledynedalsa.com

Americas Europe Asia Pacific

Boston, USA Krailling, Germany Tokyo, Japan Shanghai, China
+1 978-670-2000 +49 89-89-54-57-3-80 +81 3-5960-6353 +86 21-3368-0027
[email protected] [email protected] [email protected] [email protected]

Teledyne DALSA has its corporate offices in Waterloo, Canada

Teledyne DALSA reserves the right to make changes at any time without notice. Teledyne DALSA © 2014.