Kennedy’s Confection Editor Kiran Grewal reports on the development of technology like image processing solutions to create high quality confectionery products.

In a world driven by efficiency, productivity and marketing tools showcasing the idea of “perfection”, whether it be a person or a product, consumers today simply won’t tolerate faults and damages. And when brand integrity is as delicate as a chocolate flake, what challenges are confectionery manufacturers finding when inspecting their products and how can new technology make this process straightforward and less time consuming? Confectionery products typically come in small boxes and packs and must therefore be handled carefully during production and packaging processes. The product handling capabilities of detection equipment are an important consideration for manufacturers in this area to avoid damaging the product. 

Brands are built on consumer trust. A very quick way to lose that trust is to deliver poor quality or unsafe products to the market. Detection of contaminants is therefore a critical process within the overall goal of building and maintaining high levels of brand integrity with consumers. The provision of high quality, safe products should be non-negotiable, and compliance with a wide range of legislation and standards regulation through product inspection excellence goes a long way to safeguarding brand reputation. On a purely commercial basis, detection also helps to reduce the risk of having to implement a product recall, with all of the cost, waste, embarrassment and reputational damage that these entail.   

I spoke to Dr. Stephan Strelen, CEO of Strelen Control Systems GmbH, where he tells me metals and high-density materials are easy to detect, but the trouble actually lies in organic materials. “It is easy to detect metals with metal detectors or materials with a significantly higher density than the food product, such as stones, glass, metals, with x-rays. But the detection of any other kind of material usually requires an individually tailored solution.”

Quality requirements for trade and retail have increased dramatically in the past few years with higher rates of recalls and higher penalties. “Expectations of customers and retailers alike are high,” Stephan agrees. “For this reason, we expect a lot of investment in weighing and detection technologies and equipment. One area is the detection of foreign particles, this will increase as the technologies to detect such foreign bodies are continuously developing. The other area is the detection of ‘unattractive’ products which don’t ‘look nice’ for no easily quantifiable reasons. Deep learning and artificial intelligence offer exciting new procedures here,” he explains. 

Daniela Verhaeg, PI Communications Marketing Manager, Mettler-Toledo Product Inspection says: “Of course, contaminant detection is the main driver to ensure product safety, but inspection equipment is also used to carry out integrity checks (for example, identifying damaged packs or counting chocolates in a tray) and perform label inspection. These help manufacturers to maintain compliance with regulations and ensure that consumers benefit from safe, high quality confectionery products. Importantly, the inspection equipment gives confectionery manufacturers inspection data in real-time, allowing them to intervene and make adjustments as necessary early in the process, saving time and costs. 

Product handling can also pose a challenge to sorting systems too, Christian Hofsommer, Area Sales Manager at TOMRA explains: “Each company has its own requirements and environmental conditions, which means that standard requirements are always supplemented by specific requirements, depending on origin of products, channels of supply, or production changes (perhaps because of product innovations). Our machines can be located on the line before or after the product is oiled, depending on the factory layout, but oiling can make the product sticky and sorting trickier. This demands a very particular type of product handling. We resolve this by using specialised feeding and discharge systems. These ensure the smooth product flow essential to achieving the best sorting performance.” 

How is the market developing? 

As per the study of Maximize Market Research, the optical sorter market was worth USD 2.31 billion in 2021 and is expected to reach USD 3.30 billion by 2027, with a CAGR of 5.5% by 2027. The growing need to increase manufacturing capacity by decreasing delivery and processing time is driving up demand for optical sorters in the food industry. Various regions’ governments are getting increasingly concerned about food safety. Sensor-based optical sorters can identify and eliminate foreign matter, unwanted rot, forestation faults, and damage regularly. 

The food industry held the greatest share of the optical sorter market, and MMR believes this predominance is expected to continue over the forecast period. Growing demand for high-quality food with a faster time delivery, strict food safety laws, and automation are all primarily driving the rise of food sector applications. 

Stephan gives us an insight into the types of image processing solutions available, and what they are best suited for: “Colour image processing is a technology that can detect foreign particles as long as they are a different colour to the product. It can be used to detect impurities in sweets and confectionery as, for instance, plastic particles, chips, threads, filaments or insects, spiders, or other small animals. These kinds of particles can be easily detected with colour images as long as they’re in a position where they are visible,” he says.   

I hope I am not the only one who positively shuddered at the thought of a spider in my chocolate bar, but the real pressing question I had was what if the foreign particles are of the same colour/hue as the product? For instance, white plastic particles in white chocolate or white cream?

“Yes, this brings us to the second solution digital image processing can offer,” Stephan laughs. “Advanced colour image processing is where wavelengths outside the visible spectrum are analysed using, for instance, infrared cameras. Another alternative is analysing complex combinations of different colour spectra using multi or hyperspectral cameras. Using these technologies, foreign particles of the same colour as the product can be detected, such as white plastic in white chocolate or brown nutshells among brown nuts. Additionally, mould infestation and rotten spots can be detected,” he explains. 

The system learns and subsequently is able to form its own judgments on the beauty or desirability of the product”

“Another very up-to-date alternative is the analysis of elaborate patterns using complex algorithms, including deep learning trained neural networks. Using this technology, things such as shell-nut-differentiation are possible but also judging and evaluating the overall impression a product makes, Stephan says. 

Consumers make buying decisions based on a number of factors, one of which is how visually appealing a product is. Stephan suggests this appeal is difficult to quantify in measurable data, and it actually goes beyond factors such as colour, shape, flawlessness. “Judgement might be based on colour and shininess, colour gradients, etc. Customers may prefer an appearance that is maybe more rustic, with a ‘hand-made-impression’ in one product, perfect, smooth, and symmetrical in another. It might be based on the distribution of the topping – sugar coating, sugar pearls, or other decorative elements. Since all of these details cannot be taught to the detection system individually, deep learning is used.”

“A trained and well-versed quality management employee evaluates a number of products according to their ‘beauty’ (all kinds of scales are possible here – such as ‘good – ok – bad’, school grades, quality classed, or simply IO-NIO) and enters his/her judgement into the system. The system learns and subsequently is able to form its own judgments on the beauty or desirability of the product,” he says. It is noteworthy that not only the appearance and quality of the end product can be judged but also the appearance and quality of the raw materials such as cocoa beans. 

How has technology advanced weighing and detection processes? 

Detection techniques and technologies have improved in a number of ways. “Weighing systems such as check weighers can perform more accurate measurement at high speeds through a new generation of load cells; x-ray and metal detection systems are capable of increasingly sensitive detection through improved software algorithms; detection systems are becoming smaller and more affordable, and can be integrated with additional detection capabilities through the advent of ‘combination’ systems, which can, for example, match check weighing with metal detection in a single unit,” explains Daniela Verhaeg.   

There has also been a move towards more automation. Manual processes are known to be slow, labour-intensive and prone to human error. Efficient manufacturing is important in all sectors, and automation enables faster, more accurate and more efficient production. The nature of product inspection today is characterised by high levels of automation.

“Sorting technologies achieve an accuracy that manual sorting simply cannot. And at the same time as looking over the production line like guardian angels, automated sorters also enhance product hygiene, solve labour-related challenges, increase throughput, maximise yield, and gather data that can unlock further improvements in line efficiency,” says Christian Hofsommer. 

He adds: “In addition to taking care of food safety and product quality, sorting machines also help solve the challenges traditionally associated with employing manual sorters – an effective pill for headaches caused by labour scarcity, cost, variable effectiveness, and absenteeism. And whereas manual sorting is unavoidably subjective, imperfect, and more vulnerable to error when labourers are tired or bored, automated sorters can work for hour after hour with superior accuracy, consistent standards, and unflagging efficiency. 

“So yes, for these reasons, there is a move towards automated sorting, and this trend will only strengthen in the future. At the same time that consumers are getting pickier about food quality standards, it is getting more difficult in many parts of the world for confectionery producers to recruit and retain workers for tasks such as sorting.” 

Daniela says there are greater forces at work too. “Supply chains are becoming increasingly digitalised in general, and food safety is no different. While still in its nascent stages, food safety digitalisation – enabled by real-time data collection and networking from production systems such as product inspection machines – is without doubt a major trend in the wider food and beverage manufacturing industry. Confectionery companies are not immune to this imperative. Their customers and end-consumers will demand greater supply chain transparency, and automated product inspection technology will have a key role to play.” 

The future of weighing and detection systems? 

Technology and detection systems are constantly being developed to meet market demands. In confectionery, the requirements are usually for compact, high-speed and highly sensitive product inspection systems with advanced product handling capabilities. Not to mention, today’s confectionery market is being changed by the need for sustainability. More people are now aware that it is crucial to reduce energy use and greenhouse gas emissions and take better care of our planet’s limited resources. Retailers and consumers want to see food manufacturers addressing these concerns by implementing sustainable business practices and taking active measures to minimise food waste. New technologies will help achieve this, and so too will the gathering, analysis, and application of data. 

“Confectionery manufacturers can expect more developments in these regards, alongside further advances in combination machine technology that help companies with limited floor space to pack more product inspection into their plant. The digitalisation of the supply chain previously mentioned will see increasing progress with software integration and cloud-based networking, linking product inspection into ERP and other systems that will make supply chain transparency, facilitating instant track and trace, a reality,” muses Daniela.

“That’s why all of our sorting platforms are connectable to TOMRA Insight, a web-based data platform that gathers sorting data in near real-time and stores this securely in the cloud,” agrees Christian. “Live data can be reacted to immediately (and remotely) to optimise machine settings; historical data can be processed into actionable information to unlock improvements in machine performance,” he says.

The extent of these improvements varies according to the type of food product being processed, but the potential is huge. “Downtime can be reduced by monitoring machine health, supporting the management of predictive and condition-based maintenance, and preventing unscheduled machine shutdowns. Throughput can be maximised by evaluating throughput variations to optimise sorting equipment. Operating costs can be reduced by identifying gaps in production and analysing root causes. And sorting to target quality can be enhanced by having accurate material-composition data. Such data analysis will become increasingly valuable as we move into a digitised future, with the power to transform sorting from an operational process into a strategic management tool.” 

The growing importance of data, digitalisation, and machine networking will further accelerate investments in machine technologies such as optical sorters. And these investments will pay back by making food production more resource-efficient, more cost-efficient, and ultimately more profitable.   

Editorial contact:
Editor: Kiran Grewal