Some applications are better suited to one type of machine vision system versus another. Here’s how to evaluate systems and cameras to achieve your goals.
From Teledyne DALSA
Editor’s Note: This article is adapted from the white paper, “Smart Cameras for Manufacturing.” Download the free, full white paper that provides comprehensive explanations about five key traits that are important for smart machine vision cameras.
Machine vision uses cameras, processors and software to replace human vision on manufacturing tasks that are rapid, repetitive and precise.
Machine vision systems were first developed in the 1970s, but their size, complexity and cost limited their adoption. Introduction of digital cameras in the 1990s and ever-improving processors and software made machine vision inexpensive, robust and easy-to use. Cameras and processors continue to improve, driven by the demands of personal electronics such as PCs, cell phones and smart devices.
The smart camera is the latest evolution of machine vision, combining a camera, processor, software and communications in one small, low-power package. Let’s use a bottling line as a sample application of machine vision to illustrate one way this technology can be applied.
Pass (or Fail) the Bottle
On a bottling line, bottles are labeled, filled and closed (capped) at speeds well beyond human vision. In approximate order of difficulty, some machine-vision tasks include:
- Verify the product by reading a barcode.
- Check the presence and quality of a label.
- Verify the date and lot code.
- Check for proper closure.
- Check the “lip” of the bottle for damage.
- Check printing or seal on each closure.
- Look for foreign material in the bottle.
Financial and practical considerations drive the amount of machine-vision inspection is applied to a bottle. For example, faded printing might cause a consumer to pick another bottle, but foreign matter in a pharmaceutical might cause injury and an expensive lawsuit.
We distinguish two levels of smart cameras, based on capability and price:
A vision sensor is a specialized smart camera that provides a limited function (operations) in a single view (image). This limited function might be reading a barcode on a bottle, reading the date and lot code, looking for the position of a label or checking that the bottle’s closure (cap) is seated by measuring its vertical position. Single view means that only one image is used per inspection cycle.
In addition to the elements of a smart camera, a vision sensor might have options for built-in lighting and inexpensive lenses. If you’ve done any machine vision work, you know that lighting is a critical part of any vision system. Integrating these elements and having only a single function in a single view keeps system cost low and simplifies setup.
A smart camera vision system (SCVS) has a single view, but provides many functions on that view. In our bottling example, a single SCVS could check the presence and position of the label, read the barcode and verify the date and lot code. If an item, such as the barcode, isn’t in the SCVS’s field of view (the area the SCVS can see), a second SCVS could be used to view and read the barcode.
For demanding tasks, such as high-speed printing inspection or functions requiring integration of multiple views, a standard vision system can be used. A vision system is not a smart camera, because it consists of a larger, higher-performance processor connected to one or more standard cameras.
A vision system can process multiple views — camera images — with many functions for each view. For example, with four cameras in a vision system, you could combine four views of a bottle to inspect the “lip” of the bottle for damage.
Keep These 5 Key Features in Mind
Before you invest in a smart camera solution, however, it is critical to understand how you’ll use the data the application provides; the environment in which your vision system will operate; the expertise level of the team that will program, use, and maintain the system; and even the budget available to invest in the system and its deployment.
These are five important criteria to keep in mind as you consider whether a smart camera system is the solution you need.
1. Will a smart camera meet the processing speed and throughput requirements of your application?
2. Will the smart camera deliver the image sensor resolution needed for your application?
3. Does the smart camera offer the software tools required by your application, and once deployed, will the smart camera system be easy to program and maintain?
4. Does the smart camera system support your required communication protocols?
5. Does the smart camera system make it simple to migrate my application to a more powerful camera if needed?
Smart cameras are designed to take some of the guesswork out of component selection and system design, allowing manufacturers to focus on what’s most important: the application.
Teledyne DALSA, based in Billerica, Massachusetts, is a participating Encompass™ Product Partner in the Rockwell Automation PartnerNetwork™ program. The company provides machine vision components and solutions including image sensors, cameras, acquisition boards, sophisticated vision software and intelligent vision systems.
The Journal From Rockwell Automation and Our PartnerNetwork™ is published by Putman Media, Inc.