Expensive fruit will help you remember the number for expensive fruit
German researchers have developed intelligent self-service scales for supermarkets, able to recognize fruit or vegetables placed on them. The scales automatically recognize the item being weighed and ask the customer to choose between only those icons that are relevant, such as various kinds of tomatoes. The scales are equipped with a camera and an image evaluation algorithm that compares the image of the item on the scale with images stored in its database. Store managers can add items to the database. The scales are now being tested in about 300 supermarkets across Europe.
What was the number you were supposed to enter for the chili-pepper on the self-service scales? Was it 67 or 76? And the number for the bananas? The latest self-service scales automatically recognize what the customer has placed on them.
A quick stop at the supermarket: Balancing bananas, peppers and tomatoes in your arms, you rush from the vegetable counter to the self-service scales in order to print out the respective price label. But what was that number again, the one you had to enter for the tomatoes?
There will soon be an end to this constant running back and forth between the vegetable counter and the scales. Working on behalf of the industrial weighing company Mettler-Toledo, researchers at the Fraunhofer Institute for Information and Data Processing IITB in Karlsruhe have developed a webcam module for self-service scales. “The scales automatically recognize which fruit or vegetables are to be weighed and ask the customer to choose between only those icons that are relevant – such as tomatoes, vine-ripened tomatoes and beefsteak tomatoes,” states IITB scientist Sascha Voth. Customers can confirm the correct variety on a touch screen.
But how do the scales know whether the customer has placed a pepper, a tomato or a kiwi fruit on them? “The goods are registered by a camera integrated in the scales. An image evaluation algorithm compares the image with stored data and thus automatically recognizes which type of fruit this is,” says Voth. Even the cloudy plastic bags in which the fruit may be packaged at the counter are no problem for the scales – the image evaluation system recognizes the various types of fruit and vegetable anyway.
However, though this initially sounds straightforward, it actually involves a number of challenges: Many types of fruit are a different color depending how ripe they are. Bananas, for instance, range from a uniform green to yellow or even spotted brown. Other types of fruit such as apples and pears come in numerous varieties that can likewise vary widely in color. “The new scales are very tolerant to fluctuations in color and brightness. The module can be employed under many different kinds of illumination and with different kinds of camera. Supermarket employees can of course extend the selection of fruit recognized by the scales to make it include new varieties,” says Voth. The scales are currently being tested in about 300 supermarkets across Europe.