The program detects defects in fresh produce, even if it looks perfect to the human eye
You’re looking for bruises on an apple or squeezing an avocado at your local supermarket, but they’ve likely already been scrutinized — inside and out — by artificial intelligence.
The new software can analyze every aspect of fruits and vegetables before they reach supermarket shelves. It can determine the shelf life of the product, check for the presence of indoor mold and pesticide residues.
It integrates advanced sensors and optics into 360-degree cameras that see far more than the human eye, and that means a drastic reduction in food loss.
Up to one fifth of fresh produce goes missing before it reaches the grocery store. This is because it is poorly handled and stored in transit, or rots during its journey from farm to retailer.
The system that processes fruits and vegetables before they are distributed to the supermarket is very old. Most often, the product is manually sorted on conveyor belts before it is distributed to retailers.
One person checks 15-20 tons of products per hour manually. Sorting through over a hundred tons of produce per day at a brisk pace is a tedious task, and workers are understandably prone to making mistakes and missing out.
Says Amir Adamov, CEO of Neolithic age.
“The supply chain of fruits and vegetables is the most wasteful, because produce is the most difficult category of grocery to manage.”
The Herzliya-based company is developing software to be implemented in sorting and automation equipment in warehouses and packing houses. Its AI measures the physical appearance of a product and whether it fits what the market wants in terms of shape, shape and size, as well as its nutritional standards, including starch, fat, sugar, biomaterials and fibre.
It looks for anomalies, such as the uneven distribution of the liquid, which means that although the fruit looks perfect on the outside, it is poor on the inside. The AI also measures residual levels of chemicals and pesticides to verify that the fruit is safe to eat.
“Major stores and retail chains have hundreds of the same product, which makes it very difficult to maintain a high level of insight,” Adamoff tells NoCamels.
“We are located in different supply chain links, such as packing houses and distribution centres, and offer the best possible insight.”
Two pieces of fruit can look physically identical, but still have very different traits. He gives an example of two identical avocados, one with a three-day shelf life and the other with an eight-day shelf life.
Adamov says the software has an accuracy of 90 percent, although it varies with the product. Compared to checking tons of produce by hand, it’s very consistent, he says.
Neolithics places more emphasis on efficient scanning of fast-moving products such as tomatoes, cucumbers and potatoes – the most consumed products. Pineapple and other fruits with thicker peels are difficult to decompose.
Since the software seamlessly integrates with automated equipment, the efficiency and speed of packing houses will not be compromised. Other solutions, which include complementary apps or mobile devices, can slow things down.
Neolithics is currently working with some of the largest retailers and packing houses in Israel to determine the best distribution schedule for dozens of fruits and vegetables. One retailer was able to cut its monthly quality control budget by more than 80 percent by using scanning technology in its warehouse.
I recently started working with Granot, the largest avocado grower and exporter in Israel. Granot, which grew 30,000 tons of avocados in 2021, can now predict with up to 90 percent accuracy when an avocado will ripen.
The company plans to sell the best practices that it developed in Israel abroad, starting with the European supply chain.
“As we move forward, we hope to provide suggestions to help build better and more practical supply chain partnerships to help customers distribute to the right destination, get the best prices, and reduce food waste — the most important thing,” Adamov says. .
Neolithics was founded in 2020 and is now raising its first round of venture capital from investors and OurCrowd. The funds will be used to continue research and development, and start direct sales in the United States and Europe.