Tag Archives: AI

An X-ray and AI scanner finds holes and needles

The Australian strawberry industry has been hit by ‘sabotage’ this year: recent weeks consumers have over a 100 times found large needles stuck into the berries. To ensure the confidence in Australian berries, the producers have therefore begun to control strawberries for export with X-ray. X-ray inspection of food
is an old and well-established technology, but today you have to develop unique solutions for each product to be able to test for different errors. For example, one solution is used to find out if a potato is hollow, while an other solution is used to find out if cold cuts are contaminated with metal shavings. Therefore, X-ray inspection today is preferably used on expensive products with known types of errors – or to sabotaged strawberries.

But people behind a new Danish project, are working on a solution, where food will be able to be scanned with cheaper all-round inspection machines in the future. The Danish project will develop a new dynamic X-ray technology that can continuously vary the X-ray energy of the device and choose the right camera technology. By adding artificial intelligence, the goal is to eliminate the need to develop unique software solutions for each product, and instead enable the system to automatically distinguish good products from contaminated.

The system chooses by itself!

“We develop artificial intelligence algorithms that can choose the optimum x-ray power and right camera with the right resolution. This means that we can control many different types of food without changing the inspection system”, says Brian Vinter, professor at Niels Bohr Institutet. Aarhus-based Magnatek is responsible for the development of a new type X-ray source, while QTechnology from Copenhagen is developing cameras for the project. Newtec Engineering in Odense is responsible for system integration, and Niels Bohr Institute is heading the software development.
The Danish Technological Institute will  validate the final solution, and the project has a total budget of 17 million DKK. “One of the big challenges is to get X-ray sources and cameras to communicate with our algorithm at very high speeds. For example, we work on detecting hollow potatoes, which needs to inspect 22 tonnes per hour. Our plan is to try to make a hardware solution, so image recognition takes place directly in FPGA chips, so we do not have to have a large server standing between production lines, “says Brian Vinter. When an X-ray inspection system can handle many types of food, the price will also be lower. Therefore, Brian Winter hopes that on the long-term, inspection systems like this also can find their way to supermarkets, to make extra quality checks before the goods arrive on the shelves.

If you want to read about a company that are applying AI on food production lines, then read this interview with Rufus from Sensomind

Original article from https://ing.dk/ 

Photo by Johnny Martínez on Unsplash


In many countries, especially here in Denmark and EU, we don´t have to worry about when we get the next meal. Many of us have the possibility to pick and chose what we want to eat, and when. So in the age of self-realization, we can now use tech to make sure that we eat healthy, or least try to.

“One quarter of what you eat keeps you alive. The other three-quarters keeps your doctor alive” – Source unkown

Eating healthy starts with understanding what you’re eating on a frequent basis, but we all know that tracking what you eat, and trying to determine the nutritional information of certain meals requires a significant amount of effort. And a lot of data handling. So companies are developing apps and new tech, to let you monitor our own health. Many of these products are still in their infancy, so the data collected have to be taken with a grain of salt, but they offer an important glimpse into the future of self-regulation and personal health management.

Why is this important in the light of transparency?

If we can monitor what our body, with precision, consumes of sugar, pesticides, non-organic etc, it will have a reverse effect. When Millennials adopt health apps, that will make them much more interested in knowing the source of their food. With a never growing population of consumers with food allergies, they are demanding a clear information about reliable information. And with the growing interest in sustainable, organic, and local food, there is a pressure from consumers that value eating organic and/or sustainable, on the industry, to ensure that it really is organic, or sustainable.

“If everything is known, if it is known what is inside a product and its health effect on the body, that will really be a big change in the industry as we know it” – Nard Clabbers, Senior Business Developer at TNO

One of the companies trying to deliver precise transparent meal nutritional content is AVA. AVA uses artificial intelligence to allow users to take a photo, with their smartphone, of their meal to get instant information about the meal´s nutritional content. This is just one example, with other tech companies and startups applying blockchain, machine learning (ML), big data, argumented reality (AR) and virtual reality (VR).

Next week, you can read more about AVA and the tech companies and startups that are paving the way for more transparency of the food we eat. It might not be the companies business models, but it will be great side-effect with the focus on personal nutrition.



Book: Our Food Our Future – Eat better, waste less, share more; (2017) Alan Watkins & Matt Simister.

Photo by Dan Gold on Unsplash

Interview – Founder of SensoMind, Rufus Blas

We love the new technologies here at MyFoodTrust, of course in relation to improving the current lack of transparency. Last week we talked to Daniel from Bext360, and their use of blockchain and AI. Today we focus on AI again, which we find super interesting as a tool for food transparency, so it was a no brainer to do a interview with Rufus from SensoMind.

Read here, how SensoMind have applied AI to create a system to detect anomalies in food products and what role AI will play in creating transparency in food supply chains in the future.

Can you start with telling us a little about yourself and SensoMind?Hi, my name is Rufus. I’ve been involved in AI ever since I studied at MIT in 2004 at their Artificial Intelligence Lab. I hold both a PhD and an MBA and have a passion for innovation management and entrepreneurship. Previously I worked a lot with perception for self-driving vehicles in agriculture. I founded Sensomind with my partner in 2016 in order to democratize AI and get it out to the masses.  We’ve built our own set of tools around top AI products such as Googles Tensorflow which we thought at the time were too much targetting data scientists and not enough the engineers that are out in the field today. Our core competencies lie in analysis of complex sensor data. This is available in abundance in manufacturing so is one reason why we have gotten into this industry.

Rufus Blas
Sounds interesting, but can Sensomind’s AI technology be applied on food?
We’ve been working extensively with food manufacturing customers where our technology can be used for quality monitoring and sorting of food products. Most of our solutions are based on optical sensors (Such as cameras and multi-spectral imaging). Vision technology has been around in the food industry for 10-20 years but it’s been very difficult to apply it to food products with organic shapes and high variety. Examples include monitoring breads, meat, and fruits & vegetables. With AI you can teach the system just be showing it examples which opens up for completely new applications. An example can be automating the cutting of meat.  The price of a final product has a large influence on the cutting being done correctly and it can be very difficult using traditional computer vision to recognize exactly where to cut.
And in relation to that, can Sensomind’s technology help tackle the problem of, e.g. food contamination or unapproved enhancements/additives in food?
So we have a system to detect anomalies which can for example detect contaminants. In the food industry we have used this to detect contaminants such as bone fragments, metal, plastic, and other objects which shouldn’t be there. Unlike a human operator, our system never tires. Unapproved additives is difficult to detect using traditional color cameras so here we work with spectrometers or multi-spectral cameras. Using traditional computer vision an engineer would normally sit and try to make a model for different additives based on a pre-conceived notion of what to look for. AI allows a more statistic and data-driven approach which reduces the chance of unapproved additives making it through the production undetected.
In your opinion, what role does new technologies, e.g. AI, play in creating transparency in food supply chains?
Supply chains are notoriously difficult to model because of large amounts of often poor quality or missing data. AI is really good at crunching numbers and extracting meaningful informations from poor quality and multi-source data (including images, text, numbers, etc). AI can help piece together the information about specific products which would be impossible to model by hand.
If someone was interested in learning more about the work you do, where can the find more? 
The obvious thing would be to contact me. Check out our website (sensomind.com). We have a number of international projects going so location is often not a big issue.
A big thank you to Rufus, and great to hear of the use of AI in the food supply chain. Here at MyFoodTrust, we are always looking for how new technologies can enhance transparency and traceability.
So if you know of any startups, please let me know!
Have a great day.
© MyFoodTrust 2018