Six steps to reliable integrated machine vision systems

Inside Machines, vision tips: Machine vision technology advances have made machine vision implementations easier than before, and track and trace inspection applications can offer high speed and high accuracy. Other technologies can be integrated to extend functionality, according to information from a 2016 System Integrator of the Year, Matrix Technologies.

By Mark T. Hoske October 10, 2016

Accuracy of vision systems used to verify food and beverage product labels is critically important to those with allergies to certain ingredients or substances. Reading barcodes on shiny cans (called brightfield inspection) traditionally required specialized systems of high cost, but Matrix Technologies, a 2016 System Integrator of the Year, offers advice and integrated technologies for easier and lower cost machine vision implementations. These can ensure the correct label is securely attached to the properly coded metal can, ensuring that the label matches the contents of the container. This type of verification is often required for regulatory compliance and traceability applications. 

Machine vision reliability in six steps

  1. Use off-the-shelf industrial prepackaged vision systems; some can handle up to 1,000 cans and product codes per minute.
  2. Don’t worry; it’s easier than it used to be. Configuration and use are easier and more reliable than higher level customized systems. Customers often have expertise or staff to reconfigure the system without additional help from a system integrator.
  3. Machine vision software with the ability to do geometric pattern matching can verify a machine-printed product code.
  4. Machine vision software also uses optical character recognition (OCR) to verify product codes and multiple product labels using pattern recognition to help with varied orientations.
  5. Such machine vision systems can be industrial-grade, often with an IP67 rating to withstand dusty and wash-down environments.
  6. Integrate other sensors, controllers, and visualization as needed for the application. Other technologies, such as a laser sensor, can detect if a label isn’t properly glued to a can. A proximity sensor can trigger both the laser sensor and vision system. A controller can send a signal to reject products that fail. A human-machine interface (HMI) helps with setup and operations and can feed information to other systems.

Edited by Mark T. Hoske, content manager, CFE Media, Control Engineering, mhoske@cfemedia.com, from information provided by David J. Bishop, president and a founder of Matrix Technologies and member of the Control Engineering Editorial Advisory Board.

MORE ADVICE

Key concepts

  • Machine vision isn’t as difficult as it used to be.
  • Track and trace can be high speed and provide high accuracy. 
  • Other technologies can be integrated to extend functionality.

Consider this

What aren’t you seeing clearly, accurately, or quickly enough?

ONLINE extra

Learn more about Matrix Technologies, a 2016 System Integrator of the Year winner. 

See the Global System Integrator Database listing for Matrix Technologies.


Author Bio: Mark Hoske has been Control Engineering editor/content manager since 1994 and in a leadership role since 1999, covering all major areas: control systems, networking and information systems, control equipment and energy, and system integration, everything that comprises or facilitates the control loop. He has been writing about technology since 1987, writing professionally since 1982, and has a Bachelor of Science in Journalism degree from UW-Madison.