Microsoft Cortana Deep Learning, Image Detection and Internet of Things (IoT) in Liebherr Smart Refrigerators


Smart Refrigerators

How many times have you returned home and found that you are short on milk or eggs or other grocery when you open your refrigerator? What if your fridge told you what you are short on and with advanced e-commerce integration order your grocery through Giant or Amazon or another favorite store? Smart refrigerator concept is not new and we have all heard such use cases of Internet of Things (IoT).

So what’s new? 

Microsoft is taking the smart refrigerator concept to a new level by applying Cortana deep learning to the information gathered from inside the appliance. Deep learning goes beyond just helping you with inventory of food and may enable predictive analytics based on your behavior and tell you much in advance what to buy and in conjunction with external data, it could also predict your health based on your food buying trends.

Microsoft is partnering with Liebherr appliances digital division to develop a SmartDeviceBox which is an IoT communication module that would fit into Liebherr refrigerators. The box will communicate with the internet and is designed to be modular so the unit can be integrated and upgraded within appliances as new capabilities an enhanced performance are needed for new digital applications.

T. J. Hazen, Principal Data Scientist Manager at Microsoft in his blog wrote that this system is still in development :

Although the current system is a prototype, the deep learning technology it uses is already very powerful and rapidly maturing. Liebherr and Microsoft are actively improving these technologies to turn the newest generation of refrigerators into smart appliances that don’t just cool your food but interactively help you with your food management.

SmartDevice capability will help Liebherr refrigerator customers in shopping and planning meals with intelligent food management. Microsoft’s computer vision and deep learning capabilities will monitor groceries through internal cameras and object recognition technology. The images that are captured will be identified as food items and automatically added to an inventory list. The customer will get instant notifications on what is running low or going bad in the fridge so replenishments can be ordered. The SmartDeviceBox voice module can also help the customer in adding groceries from anywhere through an app on iOS, Android or Windows devices.

As per T.J. Hazen:

Starting with a general purpose computer vision model learned from millions of generic images, the Microsoft system can learn to recognize new types of objects – milk cartons, ketchup bottles, pickle jars and much more – from example images. When a new image from inside a refrigerator is provided to the newly learned model, it can detect the presence of the objects it has seen before during training.


Open Source Deep Learning and Artificial Intelligence

Earier in 2016, Microsoft open sourced the Artificial Intelligence (AI) framework which is used in Cortana and Skype so data scientists can push the envelope on deep learning and use, modify and enhance Microsoft’s code.The framework is called Computational Network Toolkit (CNTK) and can be used to build custom models for new use cases specially for Artificial Intelligence purposes. Google is also increasingly using DeepMind deep learning algorithms for AI applications in healthcare and data center.


Microsoft CEO Satya Nadella has been pushing the case for Cortana, Machine Learning and Artificial Intelligence to improve the global society. At the Build 2016 conference in San Francisco, Nadella said :

First, we want to build intelligence that augments human abilities and experiences.  Ultimately it’s not going to be about man versus machine.  It is going to be about man with machines; each of us excel at very different things.  The fact that we have creativity, empathy, emotion and judgment that can then be mixed with fast computation, the ability to reason over large amounts of data and do pattern recognition fast.  It’s that bringing together that I think is going to help us move our society forward.

As per Hazen, Microsoft’s deep learning technology is now the cornerstone of a wide variety of products, including the Microsoft Cognitive Services Computer Vision API which can annotate new images with a wide variety of generic category labels and object tags. Microsoft is using this capability in the Liebherr smart refrigerator project.

This will be an interesting project to watch. Get ready for a smarter meal experience!

Are you an expert in IoT, Big Data, Virtualization, Cloud, Mobile, Artificial Intelligence and/or IT technologies?Do you want to feature yourself or your content on Do you have products you would like to showcase to our visitors? Or simply do you want to share your comments with our readers? We want to hear from you and have both free and sponsorship opportunities for you and your products. E-mail us at to join the fun.

Leave a Reply

Your email address will not be published. Required fields are marked *