by Evan Lubofsky

With so many vision sensors available today, it can be a daunting task to figure out which one is right for your particular application. Will the product you're evaluating handle the variable conditions that exist in your plant? What are the latest networking capabilities to look for? What types of accessories and product support options are important?

Whether you're brand new to machine vision or an experienced user, this guide will help you during your vision sensor selection process. It provides answers to 10 of the most important questions to consider, and offers valuable tips on how to evaluate specific product features.

1. What is the importance of part location tools, and how can I assess their performance?

Part location tools, available with virtually all vision sensors, are software programs used to find parts within the vision camera's field of view. This is typically the first step in any vision application--from the simplest robot pick-and-place operation to the most complex assembly verification task--and the one that usually determines whether the application succeeds or fails.

It sounds simple enough, but locating parts in today's production environments can be extremely challenging for vision sensors. This is because many variable conditions exist that can alter the way a part appears to a vision sensor, which is trained to recognize parts based on a reference or "model" image of the part. Variable conditions include part rotation, changes in optical scale, inconsistent lighting conditions and normal variations in part appearance.

2. What role do built-in network communications play, and what capabilities should I look for?

Network communications provide a number of important benefits. First, they enable vision sensors to communicate pass/fail results data to PCs at the enterprise level. Second, they enable vision sensors to communicate directly with PLCs, robots and other factory automation devices.

When establishing a communication link between vision sensors and PCs at the enterprise level, make sure the vision sensor you're evaluating supports a broad range of standard network protocols, including:

SMTP--Simple Mail Transfer Protocol capability enables electronic notification of problems that occur on the production line. For example, if 10 consecutive parts fail inspection, the sensor can send an e-mail to a computer, pager or cell phone. This provides both emergency notification that the line may need to be stopped and a second level of inspection monitoring.

FTP--File Transfer Protocol enables users to archive failed inspection images without writing custom software.

DHCP--With Dynamic Host Configuration Protocol, each vision sensor you link to the network is automatically assigned an IP address, enabling true plug-and-play performance. Sensors without this capability require an IP address to be manually assigned, which often involves having to ask an IT administrator for an available address.

DNS--This allows you to name each vision sensor. Without DNS, it may be a daunting task to keep track of all the vision sensors running on the line and may require labels to be physically applied to each sensor with the IP address.

TCP/IP client/server--This enables vision sensors to initiate the transfer of results to other devices directly over an Ethernet without any code development.

Telnet--This Internet standard protocol enables remote login and connection from host devices.

When connecting vision sensors to factory automation devices such as PLCs and robots, look for support for the following industrial protocols:

Ethernet/IP--This protocol enables vision sensors to link to PLCs and other devices over a single Ethernet cable, eliminating the need for complex wiring schemes and costly network gateways.

ModBus/TCP--Another factory network protocol that permits direct connectivity to other devices over an Ethernet.

Finally, as more and more vision sensors are used throughout the manufacturing process, it becomes important to have a centralized way of managing them. Ensure that the vision sensor you're evaluating will allow you to manage and control vision activity over the network from remote locations in the plant and beyond.

3. Does the vision sensor make it easy to set up applications and create custom graphical user interfaces?

Vision applications don't usually require extensive HMIs, but operators typically need to interact with the vision sensor in order to make modifications during part changeovers, change tolerance parameters and determine the cause of part failures.

The vision sensor should allow you to create a custom graphical user interface as you configure the system. Make sure that this can be done without having to utilize Visual Basic or some other higher-level language.

4. Does the sensor have sufficient image preprocessing tools?

Image preprocessing tools allow the user to manipulate the raw image in order to highlight desired features or eliminate undesirable features. This ability can be a key factor in the overall performance of a vision sensor and should be a part of the standard offering.

Look for products with a suite of image preprocessing tools that will enable you to provide a range of functions such as:

Improving the contrast between the edges of a part and its background

Filtering out insignificant features

Eliminating reflections that have been cast off the part surface

Smoothing rough textures

By optimizing image data in its raw form, the overall accuracy and robustness of a vision sensor can be significantly improved.

5. What should I look for in character reading and verification capabilities?

Whether you're reading stamped alphanumeric codes on automotive parts or verifying date and lot code information on medicine bottles, there are several capabilities to look for when evaluating character reading and verification tools.

Statistical font training--This capability allows you to create a single model or "reference image" from a series of images. This enables the sensor to better handle the range of normal variations in print quality, whether it has to do with poor contrast, placement variations, degradations or variations in stroke widths. Unless you can be positive that every label will be printed with the exact quality seen in the model, the ability to develop a statistical model can be crucial to the success of your application.

Image preprocessing tools--As mentioned earlier, these allow you to optimize a trained model by sharpening the edge contrast of characters and filtering out any extraneous background noise that exists in the image. Having optimized models maximizes the reliability and repeatability of the vision sensor.

Instant image recall--This enables line operators and technicians to quickly and easily view failed images on the monitor. Whether the failure is caused by a camera knocked out of position or a missing label, it's important to know immediately why a package failed so corrective action can be taken if necessary.

6. How can I determine the repeatability of a vision sensor's gaging tools?

If your application involves critical dimensional measurement, you'll want assurance that the gaging tools are accurate and perform with a very high degree of repeatability.

In addition to testing for repeatability, it's a good idea to make sure that the vision sensor has a full suite of gaging tools. This will eliminate the need to write scripted programs to develop functions that are not part of the standard offering.

7. How do I evaluate industrial code-reading tools, and what are some specific features to look for?

Today's vision sensors should offer reliable, repeatable performance on 2-D codes that have been poorly formed, degraded or those that vary in position from part to part. They should perform well no matter the type of marking method your parts are subject to (dot peen marking, etching, hot stamping and inkjet are among the most common methods) or the part surface type, e.g., glass, metal, ceramic and plastic.

In terms of specific code-reading features, you may want to ask about the following:

Code quality verification capability--Look for products that can verify code quality to established standards. This provides valuable information about how well the marking process is working.

Read-per-second rate--Depending on your production line speed and throughput requirements, you may want to verify a vision sensor's read-per-second rate. The fastest vision sensors can read up to approximately 50 codes per second.

8. What should I know about vision sensor accessories?

To ensure that your system integration process is quick and painless, look for a vision sensor with its own family of compatible accessories. This places the burden on the vendor to test each accessory and confirm that everything works together without any problems.

Accessories to look for include:

Lighting accessories--Because there are many part surface characteristics and ambient lighting conditions to contend with, your vision sensor vendor should be able to offer a variety of lighting options. A comprehensive family of light modules includes ring light modules, which provide soft, even illumination from all directions; back light modules, which offer maximum contrast between a part and its background; darkfield lights, which provide low-angle illumination for imaging of part surface irregularities; and others.

Communications accessories--Make sure that communications peripherals such as I/O modules and network gateway modules are offered that will enable easy, quick connectivity between the vision sensor and PLCs, robots and other factory automation devices and networks.

Monitors--Some vendors offer a number of sensor-compatible displays. When selecting a monitor, look for an LCD display with antiglare impact shielding and NEMA-rated mounting bezel that provides a dust- and liquid-tight seal when mounted in an enclosure.

Camera enclosures--Industrial camera enclosures offer protection from dust, high temperatures and wash-down and should be easily mounted and able to accommodate a variety of camera lens sizes and types.

9. Does the vision sensor require a PC?

Your vendor should offer a stand-alone vision sensor that does not require a PC--during configuration or in production mode. The sensor should offer true plug-and-play performance that enables you to quickly configure the application, from start to finish, right out of the box. Just as important, the vision sensor should not require you to roll a PC onto the factory floor every time changes to the application need to be made. Finally, a true stand-alone vision sensor should enable you to hook up a monitor for live image display without a PC.

10. What types of product support services are offered?

When evaluating vision sensors, look for a vendor that offers a wide range of product support and learning services. These services start with the initial assessment of your application. Important questions to consider include:

Is the representative a full-time machine vision specialist?

How will the application be evaluated, and by whom?

Is the vendor willing to expend the engineering resources necessary to qualify my application, or will that responsibility be mine?

Once selected, what product support is available to ensure my installation is a success?

Does the selected vendor offer cost-effective training alternatives such as online "self help" support, online courses, worldwide technical support and personalized on-site training?

Does the selected supplier have the track record and financial stability to maintain their role as a long-term vision solutions provider?

It's also important to look for a vendor with a global network of offices offering both pre- and post-sales support. This way, you can get the same consistent high level of product support anywhere in the world. This can be especially important if the system is commissioned in one location and shipped to another.

The Ten Most Common Vision System Problems

About the author

Evan Lubofsky is a senior writer with Cognex Corp. He has a bachelor's degree in journalism from the University of Massachusetts. He has written about machine vision and imaging technologies for more than seven years. Lubofsky's articles have appeared in more than 40 trade publications. Prior to joining Cognex, he worked for Data Translation. Letters to the editor regarding this article can be sent to letters@qualitydigest.com.

© Copyright 2002, Cognex Corp.