2 minute read

READY-TO-DRINK

Deep learning for empty bottle inspection

Anyone who works with empty bottle inspectors knows that not every bottle that the inspector rejects actually has a defect. It might simply be water droplets or a bit of foam still clinging to the bottle after cleaning.

Linatronic AI employs deep learning technology for automatic image detection

SINCE CONVENTIONAL SYSTEMS until it could accurately distinguish water thing of the past. The neural network doesn’t can’t always distinguish these from droplets from other anomalies – with a reliability require manual calibration to local conditions. contaminants or damage with 100% rate of over 99.9%. As a result, waste of material Instead, the Linatronic AI is delivered fully certainty, they tend to err on the side of caution and reject the container. As a due to false rejects is no longer an issue. The time-consuming process of configuring trained and ready to start work. •Food Manufacturing Africa, 132 x 200 mm, CC-en46-AZ416 11/19 result, in every production shift, countless the inspector during commissioning is also a Krones – www.krones.com perfectly usable bottles land in the trash.

Krones has taken the evolution of its inspection technology to the next level. The new Linatronic AI employs deep learning software to automatically detect and classify anomalies, making it much smarter and more efficient than its conventional peers.

Deep learning is a technology that enables machines to do what we humans do naturally: learn from example. But there is one big difference: a machine can use this ability many times more efficiently than humans can.

The foundation for deep learning is an artificial neural network (ANN). The ANN can be described as a complex system of multiple consecutive filters. The images captured during the inspection process are fed through these filter layers, one after the other. Each layer extracts a different characteristic of the image. Since one filter’s output becomes the input for the subsequent filter, the complexity of an image’s characteristics can be increased almost infinitely. The chain ranges from simply identifying dark or light pixels all the way to classifying very specific objects such as water droplets.

TRAINED USING THOUSANDS OF IMAGES

To ensure that the Linatronic AI applies these filters with the We embrace a holistic approach necessary precision in practice, to your beverage factory. it is trained ahead of time with pre-classified example images. In this way, its neural network learns to filter out and interpret the relevant image characteristics. The same is true for machines that is true for us humans: the more intensively you train, the better the results. Therefore, the Linatronic AI’s neural network was continually fine-tuned using thousands of example images thing of the past. The neural network doesn’t require manual calibration to local conditions. Instead, the Linatronic AI is delivered fully trained and ready to start work. •

Krones – www.krones.com

This article is from: