Skoltech scientists have created a software system designed to control the quality of fruits and vegetables using artificial intelligence. Unlike other similar systems, the invention can detect defects on the entire surface of the fruit, not just on the part of the fruit that first enters the camera's field of view.
This was achieved because the machine recognizes each object among others and follows it during all movements along the sorting line. In the course of it, the fruit is turned over and the computer assesses its condition from other angles.
"Our system is able to use a multispectral camera to detect signs of rot on fruit before they are visible to the human eye. It operates in the near-infrared range with a wavelength of 900-950 nanometers. If more sensitive equipment becomes available, we can do it even earlier. To recognize fruits and vegetables, we use artificial intelligence, which we train on images, because in fact video is a high sequence of frames," said Nikita Stasenko, junior research engineer at Skoltech's Agrotechnology Project Center.
The device uses a multispectral lens that "sees" rotting processes much earlier than a human can notice them. In this case, AI not only signals the spoilage of fruit, but also classifies it: something is thrown away or redirected for recycling.
Read more in an exclusive Izvestia piece:
Fruit schedule: AI will ensure high quality of tangerines on the shelves
