Microsoft is working with the household appliances division at equipment manufacturer Liebherr to develop a SmartDeviceBox communication module for Liebherr’s refrigerators and freezers.
The SmartDeviceBox module helps connect Liebherr’s refrigerators and freezers to the internet. This means, going forward, the module can help support shopping and meal planning through intelligent food management.
Food can be monitored using cameras and object recognition technology, recognising individual food items within the refrigerator. The data is then fed into an inventory list, and customers can quickly see what is in the refrigerator from any location.
The SmartDeviceBox also features a voice module, which allows users to add items to their shopping list quickly and easily. They can then view the full list from any location using an app on their iOS, Android or Windows device.
Modular units can be integrated and upgraded at any time in existing SmartDevice-ready appliances. This means it is easier to create value for customers via new digital features and solutions.
Microsoft is providing the deep learning algorithms for the module, which are available within the company’s open source Computational Network Toolkit and can be used to build custom models for new use cases.
Using these algorithms, data scientists at Microsoft worked with Liebherr to create a new image processing system to detect specific food products within the refrigerator. Having started out with a general purpose computer vision model, the system can now learn to recognise new type of objects from example images. This means it can see new objects in the fridge it recognises from training.
Although currently at the prototype stage, this collaboration is an example of Microsoft working to help create a new generation of smart appliances that enable a higher level of food management.
Share this story