In healthcare today, a computer can read an X-ray just as well as a doctor can – and even better in some cases. But the technology has many potential uses, such as automatic quality inspections or safety monitoring. However, before a computer vision system replaces a person, very high safety requirements must be met. Autonomous vehicles are one example.

"In many cases, the system is very good at making the right decisions quickly and is sometimes better than a human being at driving a car,” says Aleksis Pirinen, Senior Researcher in Machine Learning and Computer Vision. “Yet we still we don’t feel that the technology is mature, even though it could already, to some extent, lead to fewer deaths on the roads.”

Various and high thresholds for use

For some computer vision applications, there are ready-to-use AI models, such as for X-ray images where a computer has learned to distinguish between an intact bone and one with a fracture. But for those seeking to develop something new and specific to their business, a number of steps must be implemented.

“A fundamental point is to have training data that your AI model should train on,” says Pirinen. “For example, if you want the system to recognise agricultural plant diseases, you need pictures of healthy plants as well as diseased plants.”

And once you have your training data, you need to tell the system what it depicts by means of so-called annotations, or information about what each image contains.

For those wanting to implement or develop computer vision technology in their organisation, RISE can be a partner for teaching, collaboration, or research.

“We have many research projects through which we can demonstrate what can be done with the data and to meet the needs of the partner,” says Mogren.

Several ethical aspects

An ethical dilemma related to computer vision is bias, which is sometimes unconsciously built into the system by those who trained it. Among other problems, there have been instances where the system does not read dark-skinned faces as well as it does for light-skinned faces.

“This is of course extremely problematic, you have to work actively to minimise this kind of bias in your models,” says Mogren.

“One way could be ensuring greater diversity among those who develop the models,” says Pirinen.

Another ethical dilemma, often highlighted in the media, is the risk of ‘deepfakes’. Not only can computer vision learn to understand what it sees, but it can also create images.

“With the right skills, very realistic images and videos can be made,” cautions Pirinen. “This is something that will need to be tackled in the future.”

“As with all technology, it can be used for both good and evil,” adds Mogren. Positive uses for images generated by the systems include digital twins, which can be used in research to perform tests in a very realistic simulated environment, and images that show the potential effects of upcoming climate disasters.

“It’s a way to demonstrate how powerful these systems are, and how there are both risks and positive uses.”

Retinal imaging and weed control

Two computer vision applications that RISE helped to develop are retinal imaging as a form of drug testing, and new possibilities for weed control.

“We worked with data and algorithms to find weeds, then another operator developed a robot that seeks and destroys them using a small laser,” says Mogren.

Computer vision is an emerging technology, and we have not yet seen all the application areas for which the technology can be useful.

“Autonomous vehicles and all types of driver assistance systems are also arenas where this technology is incredibly useful. I would say that computer vision has an abundance of benefits. There are extremely wide areas of application that are only limited by our imaginations,” concludes Mogren.

The goal is to create conditions for a system change leading to an environmentally, socially and economically sustainable food sector. FINEST aim to find solutions that contribute to a faster adjustment of the food system by combining competence and co-creation between actors with different perspectives

” To launch new innovations faster, we need to collaborate from farm to consumer. At FINEST, we try to achieve this through social science and technical research in collaboration with actors from the business community,” explains Charlotte Eklund-Jonsson, Research and Business Developer at RISE.

System Innovation, System Change and Product Development

“ How can the agricultural and food sector change in all stages from raw material production, processes and distribution to value offerings and customer behaviour? To answer that, we look at different components in the system and their mutual relationship and collaboration,” says Fredric Norefjäll, Project Manager, Sustainable Business at RISE.
 

The focus is on system innovation in the food system’s value chains, social system change, and product development and business models. FINEST will develop collaborations on optimized use of raw materials, product properties, food safety, sensory analyzes, market analyzes, regulatory innovation and conconsumer insights.

“Simplified, we look at the entire value chain from different perspectives; What happens at different points and what is required for a change to occur? Then, we gather scientifically developed tools and guidelines based on different research disciplines that can help food companies take the next step towards a sustainable transition. All this is to solve problems that no single organization could solve,” Fredric Norefjäll explains.

Thomas Lennerfors, Professor of Industrial Technology at Uppsala University, says that an essential aspect of FINEST is to learn from innovation management in conversion work from other industries.

”To better understand the features of the food system, we will benefit from our previous research in innovation and sustainability in other industries, such as life science, electricity market and shipping, regarding, for instance, market regulations and what sustainable production means,” he says.

Forest Berries, Legumes and Experimental Foods  

FINEST will concentrate its innovation work linked to Swedish forest berries, Protein-rich legumes and Experimental food production. In addition to the development of product pilots, health aspects, consumer acceptance, and the regulations surrounding this type of food will be examined.

Swedish forest berries have been selected because it is an underutilized product. Although as much as ten per cent of Sweden’s land area consists of blueberry rice, only a few per cent of the berries are picked, of which a large part is exported. At the same time, Sweden imports American blueberries.

”In Asia, Nordic blueberries are popular in health food. However, in Sweden, business and product development is still quite limited, and the process industry is absent in the berry industry, “ says Sophia Wassén, Product Design Researcher at RISE.
 

”Taking care of our wild berries is about utilizing the resources available in our immediate area, says Thomas Lennerfors. He believes that Sweden’s volume and process development can increase even though many berries are picked. However, he also believes that working with wild berries is complicated as the business has struggled with legitimacy problems linked to the pickers’ working conditions over the past ten years.

“Although we see that there has been a significant improvement, it is essential to constantly consider the different dimensions of sustainability and the synergies and conflicts between them when we try to improve the use of forest berries”, says Thomas Lennerfors.

”We know that there is potential for new products and want to help local companies and the process industry see the business opportunities, such as fermented blueberry juice, powder for bakeries, berry seed oil, and shells for healthy food or extraction of anthocyanins. There are many possibilities, and together with producers, we at FINEST will develop and test several different berry processing processes”, says Sophia Wassén.

Legumes are a protein-rich food that works well to grow in Sweden, but most products today come from imported raw materials. The third value chain is about new experimental foods that do not use agricultural lands, such as fatty acids produced from carbon dioxide and energy.

”It is exciting because it involves completely new ways of producing food that reduces dependence on arable land. We want to increase the understanding of how experimental food production generally could contribute to a more sustainable food supply”, says Sophia Wassén.

”Regarding product development, it is also essential to always have a consumer focus in what we do. As soon as we refine something, whether it is berries, legumes or experimental foods, we have to think about whether it is a product that consumers will buy. So we need more knowledge about customer behaviour”,  Sophia Wassén adds.teenden, lägger Sophia Wassén till.

RISE invests in the future food system

“With FINEST, we want to contribute to innovation in the food sector by involving actors from all parts of the value chain to jointly create conditions for innovation, contribute to system change and support concrete projects,” says Charlotte Eklund-Jonsson.

“We try to help established players find new ways by collaborating in new ways and with new parties, and also reach the market faster with climate-smart, excellent and healthy food products, “ says Maria Elmquist, Professor of Innovation Management at Chalmers.

She says that Chalmers has recruited a doctoral student focusing on innovation in the food sector, who is now conducting a study together with RISE, ICA and the Household Society. The background is that more knowledge is needed about how different actors can collaborate and develop their internal processes to enable more innovations in the food system.