In the past five years, machine vision technologies have begun to play a key role in wholesale baking applications in a variety of ways. Baking industry insiders see an ever-expanding number of uses for the technology in the not-too-distant future.

One reason for the advance is the technology is expanding beyond its traditional use at automotive and other industrial assembly manufacturers. Vision technology now is being used in quality, packaging and appearance control across many other industries, including baking, says Bob Rongo, owner, Decision Technology LLC, Indianapolis.

“There's growth potential in baking because machine vision can be used for overall quality control and for verifying the final product looks right,” Rongo says. “But it also can be used within the baking process itself and for packaging. It can really be customized to fit a number of needs.”

Vision systems also increase operating efficiency on baking lines and can cut labor costs, adds Eric Riggle, vice president, Rademaker USA Inc., Hudson, Ohio.

First, a definition

Think of these systems almost as an inspector or operator on the production or packaging line. As the name implies, vision systems have the capability to see what's happening on the line, albeit in a limited way far removed from how a human relies on vision.

These systems instead use digital cameras, smart cameras and image processing software to carry out their duties. They can be programmed to perform narrowly defined tasks, such as to count objects on a conveyor or to search for defects in product or product packaging.

But machine-vision systems go beyond merely noting defects. Through software tied to other equipment and devices, they can theoretically help make decisions about and act on what they see. If a system is programmed to ensure each loaf of bread is of uniform color, for example, and it “sees” a loaf that is too light or too dark, it relays that information to a robot or an operator further down the line. The operator or robot then knows to remove that loaf from the line.

Though vision systems have been somewhat slow to catch on in American wholesale baking applications, that has been changing as bakers determine how to best incorporate this equipment into their lines, Rongo says. The baking industry in particular lends itself to a number of machine-vision applications, he adds.

The systems can be purchased separately and incorporated into existing production lines or they can come as an overall part of equipment purchased from a vendor. Companies, such as Rongo's, create customized lines, vision included, for specialized applications.

Legs and tails aligned

Four years ago, Rademaker introduced its Croissant Vision System, which ensures moulded croissants are positioned properly for the bending and pinching of croissant legs and tails.

“The holy grail of croissant production is the automatic bending and pinching of the croissant because that's where the labor is,” Riggle says. “For years that's been something equipment makers have been diligently pursuing.”

The making of croissants through the moulding procedure is easy to automate, Riggle says. But if the croissants aren't precisely positioned when entering the automated moulding system, they can't be perfectly bent and pinched by the machine.

To do this shaping by hand, the operator picks up a pre-moulded croissant and bends and pinches it to align its legs and tails properly. When made by machine, the tips aren't always correctly positioned.

With the Rademaker system, upon exiting the baking process, the unformed croissants travel past the vision system, which incorporates high-intensity lamps that cast a shadow on each croissant. The croissant shadow, when captured on camera, tells the system where each croissant is exactly positioned as it travels down the conveyor. The system then sends a signal to equipment downstream, which uses this positioning information to automatically and uniformly line up the unformed croissants. Once lined up properly, the croissants can be mechanically bent and pinched with precision.