Working things out

If a machine-vision system can help, then a machine-vision system integrator may be the answer.

Feb 1st, 2008
Th Cholton

If a machine-vision system can help, then a machine-vision system integrator may be the answer.

Conard Holton

Implementing a machine-vision system is not for the faint of heart. The challenges of integrating multiple vision and automation components into a complete system, whether on a factory floor or other location, can be complex-but the rewards can be significant cost savings as well as improved product quality and operational efficiency.

The initial, critical question that an end-user must face as they begin the evaluation process is whether the expertise exists in-house or must come from a third-party system integrator. As John Nagle at system integrator Nagle Research (Cedar Park, TX) notes, the most important thing is that a broad skill set and expertise in a variety of disciplines will be required to complete the project on time and on budget.

Nagle says it is impossible to engineer a solution without a thorough understanding of the problem. But to truly know the problem, you have to get past the superficial goals and get to the meat of the challenges that a vision solution will have to face. For example, Nagle cites a candy factory that needs a vision system to count jellybeans moving down a conveyor belt. That’s the superficial goal and a very straightforward task for a machine-vision system to accomplish.

The ability to intelligently plan a solution, however, requires much more information. What should the system do with the count? Does it need to trigger a signal when a certain count is reached? Does it need to communicate with a progammable logic controller? What if a jellybean is malformed, does it count? And how does the system determine what is a “good” jellybean? How fast are the jellybeans moving? Do you need to count the individual colors? What are the space considerations for the vision system?

Evaluating in-house capabilities is the next step in deciding how much, if any, of the project can be done by staff. If the project can be accomplished with off-the-shelf vision solutions or relatively simple smart cameras and only minor external connectivity, then the chances of being able to do this are good. If complicated record keeping, PLC connectivity, or advanced image-processing algorithms are required, it is almost certain that a third-party vision-system integrator with software-development capability will be necessary.

Nagle says that any competent vision integrator should be able to integrate vision in simple-to-moderately complex projects. Many vision integrators do not have great depth in software and electrical engineering, and so the more complicated vision projects are beyond them. It is important to match the skills an integrator brings to the table with the skills that will be required. An integrator can save a company from spending hundreds of thousands of dollars on inappropriate equipment and software.

Nagle Research, for example, was asked by a railroad-equipment manufacturer to provide consultation as to what camera would be required for a 2-D high-speed railroad-inspection system. The company had already spent many thousands of dollars on image-processing software to locate defects in cross-ties using 2-D imaging techniques. The problem was that their approach had not accounted for surface stains, sealant, and debris confusing the analysis software. Nagle ultimately concluded that a 3-D solution was more appropriate for this application and developed a SICK (Minneapolis, MN) Ranger-based solution that handles these material properties (see

For their fee, Nagle’s clients receive professional consultation, software and electrical engineering resources, and a machine-vision solution that meets their requirements. In most cases, unless specifically agreed to, the client does not get source code to the final solution. In some arrangements Nagle will relinquish source code for the application; for example, the user interface and project-specific algorithms.

Nagle says that the basic questions to be answered before he is called are: Is the project outside the scope of in-house capabilities? Is the company open to using third-party integrators? What is the price of failure or delays arising from lack of internal experience? Is there a budget for vision that includes third-party integration? Is there likelihood that given a workable solution within budget, the project would proceed?

If the answers to all of these are “yes,” then most any integrator would be willing to take the challenge. And a competent integrator is the key to a successful system.

Click here to enlarge image

CONARD HOLTON is editor in chief of Vision Systems Design; e-mail:

More in Software