Detecting Fraudulent Rice Labelling With A Smartphone Photo

Wednesday, January 22nd, 2020 | 524 Views


A simple photograph taken with a mobile phone is able to detect irregularities in the labelling of rice, according to an investigation conducted by the Complutense University of Madrid (UCM) and the Scintillon Institute of San Diego (USA). Scientists developed an algorithm based on deep learning—a field of artificial intelligence—that is able to determine whether the rice is as described.

In Europe, selling low-quality rice as high-quality rice is the most common fraud. In other cases, plastic is added to grains in quantities undetected until it is cooked.

“What we contribute compared to other detection methods is simplicity and we show the consumer that you do not need large sums of money to verify whether a certain type of rice is the one mentioned on the label,” states José Santiago Torrecilla, Professor and researcher from the Department of Chemical Engineering and Materials of the UCM.

The research is carried out using five types of rice which were ground to distinguish the type of rice not only in grain form, but also when ground into flour. Algorithms based on convolutional neural networks were then designed and optimised to process the information contained in the images for classification based on the type of rice, with final precision models between 93 percent and 99 percent.

Furthermore, this technology holds potential for many future applications in the food industry as it can be extrapolated to other types of cereals and food.

 

Check these articles out:

Azelis Expands Distribution Agreement With Roquette Into Asia Pacific

High Pressure Processing: A Powerful Tool For The Food & Beverage Industry

Spotlight On Soy Plant Protein

The Potato Is Making A Comeback

International Alignment On Halal Certification

Tetra Pak Collaborates With Hexagon In Smart Plant Engineering Platform

Market Outlook 2020: 3D Printing—A New Frontier Of Food

Ingredion To Acquire Thai Rice Starch and Flour Business

 

SHARE WITH FRIENDS: