Swiss company, QualySense - has developed a robot to inspect oats for gluten-free labeling of breakfast cereals
First published in Milling and Grain, January 2016
Health claims relate a food substance to the reduced risk of a disease or to a health-related condition, and depend on the quality of the raw materials. Here we focus on ready-to-eat ‘gluten-free’ breakfast cereals.
First published in Milling and Grain, January 2016
Health claims relate a food substance to the reduced risk of a disease or to a health-related condition, and depend on the quality of the raw materials. Here we focus on ready-to-eat ‘gluten-free’ breakfast cereals.
Some cereals are gluten-free by nature. However, they can be contaminated with gluten that is carried by grains such as wheat, barley and rye, this can happen at any time. For this reason food processors must ensure high purity levels of the end products. This is achieved by running accurate, lengthy and frequent inspections on selected samples to identify gluten contamination.
The presence of gluten requires additional processing costs and may lead to serious legal claims. Today trained personnel inspect samples to identify impurities that are generally below two percent, a procedure that is lengthy and affected by subjective biases and low repeatability.
The manual visual inspection is based on shape and color features but the variation of these parameters is often small enough to challenge even the most trained inspectors as well as detection technologies based on Machine Vision. In fact, several researchers have made attempts to solve this problem using Color Images, which resulted in non-reliable methods. QualySense has developed a proprietary high-speed single kernel analyser, the QSorter Explorer and investigated the possibility of combining Machine Vision with hyperspectral NIR.
Color images and infrared spectra between 900 nm and 1700 nm were acquired, preprocessed and classified with various algorithms. As a result, a method based on the detection of gluten with NIR combined with shape and color assessment enable the QSorter Explorer to reach classification accuracies higher than 95 percent and with very low repeatability errors. This method has been successfully tested and adopted by leaders of the gluten-free industry.
Read the full article in Milling and Grain HERE.
Read the full article in Milling and Grain HERE.
The Global Miller
This blog is maintained by The Global Miller staff and is supported by the magazine GFMT
which is published by Perendale Publishers Limited.
For additional daily news from milling around the world: global-milling.com
No comments:
Post a Comment