According to the UN’s Food and Agriculture Organization (FAO), around and one third of the food produced globally –almost $1 trillion worth– ends up in landfills. London based company Winnow is using computer vision and machine learning to help kitchens avoid waste.
So far, the technology still requires manual input. It consists of a series of scales under the food waste bin, while staff members tell the system what kind of food they’re throwing out. However, Winnow is introducing automation to the system, with a camera that takes images of the food being thrown into the bin, and then identify what it is. The information is stored in Winnow’s cloud analytics, using regular reports and the value of the waste, to determine where money could be saved.
The Winnow Vision system can be trained, as chefs and staff select the food they’ve disposed of on a list presented on the screen. Between 200 and 1000 images can be needed to train the system to recognize a food item. Some participants in the pilot project include Ikea, Morrison’s supermarket chain and Emaar in the United Arab Emirates. However, Winnow Vision is available for all restaurants and kitchens around the world to buy from Winnow.
Winnow announced that their manual system is being used by thousands of chefs worldwide, and has helped divert worth $30 million of food from landfills.
“Food waste is a global issue, and one that kitchens around the world are struggling with,” said Winnow CEO Marc Zornes. “Without visibility into what is being wasted, kitchens are wasting far more food than they think. By understanding and reporting food waste’s very real costs — both to the bottom line and the environment — Winnow Vision empowers chefs to take action.”