App On Your Phone Can Help You Verify Type And Authenticity Of Rice From Just A Photo
Shopping for groceries can be a confusing affair, especially if you aren’t a regular and are just helping your mom or partner to shop, it can be quite a process -- especially when it comes to what kind of rice to pick with so many varieties offering different kinds of flavours and textures.
However, now an AI app on your phone could help you ease this conundrum.
Researchers at Complutense University of Madrid and Scintillion Institute of San Diego, USA have created an algorithm based on deep learning that is able to detect whether the rice in an image is similar to the label on top of it.
According to Jose Santiago Torrecilla, Professor and researcher from the Department of Chemical Engineering and Materials at the UCM, "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."
To create the algorithm, researchers took five different categories of rice and ground it into a powder. This was done not just to know the grain when it’s intact, but also when it was turned into a flour.
Eventually, the finally trained algorithm was able to deliver an accuracy of 93 to 99 percent.
Jose further added, "It should be noted that rice is just one example of cereal and, therefore, this technology could be extrapolated to other types of cereals or food.”
This basically means that the same technology could help you shop for groceries other than rice with ease. This means it could be used for pulses, legumes etc. And pretty soon it may be used to determine real foodgrains versus fake adulterated pieces, too. How cool is that?