Improving Food Safety—One Can at a Time

Aug. 15, 2013
A major food processor needed a solution to improve inspection of product codes at high speeds, and also read the UPC barcode and ensure the labels were fully attached. Matrix Technologies provided a vision-based brightfield inspection system that would improve regulatory compliance and traceability.

Lactose-free, gluten-free, contains peanuts, manufactured on equipment that processes tree nuts. In a facility that produces millions of cans of food and beverages a year, getting the wrong label on a product is more than a customer satisfaction issue; it’s a potential liability.

Food processors must match the character-based product code printed on the can with the universal product code (UPC) barcode on the label. Inspection is difficult because of the large volumes and high speeds involved, and because of the difficulty reading product codes against the bright metal background.

A major food processor approached Matrix Technologies for a vision system-based brightfield inspection solution that would improve inspection of product codes at the required line speeds. The solution also needed to read the UPC barcode and ensure the labels were fully attached. Ultimately, the solution would improve regulatory compliance and traceability.

New technology recognizes patterns
We created a solution using a new type of vision system, Cognex In-Sight, that is able to inspect product codes against bright can backgrounds at a speed of 1,000 products per minute. Matrix Technologies’ bright stock labeling solution inspects products immediately after a label is applied. A pattern-matching tool recognizes a pattern regardless of its location. Rather than reading individual characters, the application looks for an image that matches the three-digit product code. The vision system can be easily configured to detect a product code anywhere within its field of view.

Our bright stock inspection solution uses a laser scanner to read the barcode on each product’s label. A fiber-optic sensor identifies improperly glued labels by detecting a protruding flap. A proximity sensor triggers both the vision system and the barcode reader. The vision system, barcode scanner and fiber-optic sensor independently inspect each product and send pass and fail signals to the programmable logic controller (PLC) that oversees the inspection station. The pass or fail signals are buffered until the product travels to the reject mechanism.

Setup made easyA human machine interface (HMI) running on a PC displays real-time image updates, inspection statistics, diagnostics and setup functions. Images are displayed on the screen with an overlay to indicate a pass or fail result. Running counts of passed and failed inspections also are displayed, informing users about each failed inspection. The vision system records images of all products that fail inspection, usually due to the improper orientation of the product code.

Enterprise resource planning (ERP) connectivity relates product codes to UPC codes. The system uses Microsoft SQL Server to centralize configuration parameters and to retain failed inspection results. Setup mode leverages the ERP and SQL Server connections to ensure that the latest updates are deployed. When the operator presses a “setup mode” button, the barcode from the next product that runs through the system is retrieved and automatically used to download the correct product code. No data entry is required.

We have deployed 10 of these systems to our initial customer. The bright stacking solutions provide accurate inspection results with virtually no downtime. Matching the images of the product codes offers a more reliable solution than attempting to convert the images to characters.

>> Les Haman is Department Manager at Matrix Technologies Inc. (, a control system integrator headquartered in Maumee, Ohio, and a certified member of the Control System Integrators Association (CSIA).