Start-up digital tools firm Winnow has launched an AI-enabled product, Winnow Vision, to ‘revolutionise’ food management in commercial kitchens.
Using a camera, a set of smart scales and the same type of machine learning technology found in autonomous vehicles, Winnow Vision ‘learns’ to recognise different foods being thrown in the bin and calculates the financial and environment cost of this discarded food to commercial kitchens.
Operators can then adjust their food purchasing decisions accordingly, reducing their spending and tackling overproduction.
The launch follows a proof of concept phase launched in January 2018 with early adopter partners IKEA, Morrisons and Emaar Properties, to test Winnow Vision’s technology in commercial kitchens around the world. Winnow and partners have been working on the technology since October 2017. The pilot reportedly proved that Winnow Vision surpasses human levels of accuracy and enables chefs to run smarter, more profitable and more efficient kitchens.
The launch of Winnow Vision follows the success of Winnow’s first device, which consisted of a set of smart scales and identified food manually. The company says it has helped commercial kitchens save more than $30m in annualised food costs which equates to preventing over 23m meals going in the bin. The new, AI-powered Winnow Vision is already installed in over 75 kitchens and the technology will be rolled out to hundreds more this year.
Marc Zornes, CEO of Winnow, says: “Food waste is a global issue, and one that kitchens around the world are struggling with. 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. Using technology that learns and improves with each use, Winnow Vision has the ability to tackle food waste on a global scale.”
With Winnow Vision, businesses install a piece of technology that can already recognise most food items and can be trained to learn other menu items in any kitchen. During the training and automation phases, the system takes human input, providing a shortlist of possible menu items for kitchen staff to select, to improve its predictions based on feedback. Over time, the system continues to improve and should automatically recognise food with no human interaction.