Launched officially on 1 June, SIS-TA introduces a fully digital and transactional sales platform for smart industry components, strategically expands STEMMER IMAGING’s existing business model by complementing its established consultative approach with a scalable online sales channel focused on speed, simplicity, and direct availability.

Responding to changing customer expectations

Industrial purchasing behaviour has fundamentally changed in recent years. Customers increasingly conduct product research, technology comparisons, and supplier evaluations digitally and independently. At the same time, expectations regarding transparent pricing, immediate availability, and direct ordering capabilities continue to rise.

SIS-TA was specifically created to address these market developments with a digital-first approach tailored to customers who require fast and efficient procurement processes for industrial automation products.

“The market is shifting from education to execution,” explains Mike Weccardt CEO, SIS- TA “Customers increasingly know exactly what they need and expect frictionless purchasing experiences with maximum transparency and speed.”

A transactional platform for industrial automation

The new online platform serves as the central customer interface, covering the complete purchasing process from product selection and availability checks to transparent pricing and direct ordering.

At launch, SIS-TA focuses on machine vision products including cameras, optics, lighting, and frame grabbers. Over time, the portfolio will expand to include additional smart industry technologies such as cobots, AMRs, industrial sensors, smart cameras, motion control solutions, industrial I/O, and PLC systems.

SIS-TA will provide AI-powered first- and second-level support to ensure fast and efficient customer assistance. For more complex projects, solutions, and applications, customers will have access to STEMMER IMAGING’s expert support organization and its highly specialised engineering teams.

Strategic expansion into new customer segments

SIS-TA is specifically designed to address customer groups that increasingly prioritize speed, price transparency, and simplified procurement processes. The platform enables STEMMER IMAGING to expand into new market segments while strengthening long-term customer relationships within the broader group ecosystem.

The operating model has been intentionally designed to remain lean, scalable, and highly automated, allowing rapid adaptation to changing market requirements and future portfolio expansion.

With SIS-TA, STEMMER IMAGING takes the next strategic step in industrial digitalisation – combining competitive products, digital sales models, and integrated services into a future- oriented smart industry platform.

For example, MERLIC enables seamless integration into various process environments and improves workflow stability through its own built-in features. In addition to new machine vision methods, MERLIC 26.03 also introduces a feature that supports the compliant execution of audit trails.

MERLIC 26.03 addresses the current requirements of the manufacturing industry as a machine vision software solution: the continuously increasing number of product variants, rapidly rising quality demands, and the shortage of skilled workers driven by demographic change all call for automated solutions such as industrial machine vision.

“We see that many companies are engaging with machine vision for the first time or much more intensively. It is crucial that the setup of such an industrial image processing system can be easily integrated into existing installations,” explains Ulf Schulmeyer, Product Manager MERLIC at MVTec. MERLIC addresses exactly these needs: the current release offers not only powerful machine vision algorithms, but also a high degree of application flexibility, performance, and scalability.

Expanding the range of machine vision applications

MERLIC has been systematically enhanced in recent years. On the one hand, MERLIC remains a standard software solution for industrial machine vision. “MERLIC provides numerous powerful machine vision algorithms that can be used to realise virtually all tasks, such as code and text reading, various quality inspections, and collaboration with robots. In addition to rule-based methods, methods based on artificial intelligence (AI) are also available,” explains Schulmeyer.

In addition, MERLIC is designed so that even beginners in industrial machine vision can quickly benefit from its advantages. This is made possible by the graphical user interface, which allows complete machine vision applications to be created via drag-and-drop. Instead of implementing or programming algorithms step by step, applications are built by combining and configuring standardized tools.

Furthermore, MERLIC follows the approach of unifying image acquisition, image processing and analysis, integrated communication interfaces, and result visualisation within a single environment. Thanks to support for common industry standards and various hardware types, applications can be developed, deployed, and operated without switching between different systems.

Connectivity, process stability, traceability

On the other hand, MERLIC goes one step further by offering functionalities that extend beyond pure image processing and support users with regard to the entire application. First and foremost is its integration capability. Thanks to various plug-ins, users benefit from simple, fast, and seamless integration of the machine vision software into existing or new production environments.

A key advantage is that no in-house programming or machine vision expertise is required. Specifically, plug-ins are available for programmable logic controllers (PLCs) from well-known manufacturers such as Siemens, Mitsubishi, Beckhoff, and Schneider Electric, as well as many other companies.

In addition, MERLIC provides features to increase the reliability of the entire machine vision application. For example, if the cycle rate on a production line is too high, errors in image acquisition may occur. Enhanced error detection in the Image Source Manager (ISM) documents missed trigger signals and detects discarded images as well as connection interruptions to devices. The software notifies users and helps them take measures to improve the stability of image acquisition.

“We are very pleased that the ‘Frontend Observability’ feature is available starting with MERLIC 26.03. It supports the compliant execution of audit trails,” says Schulmeyer. This feature is an important tool in industrial quality assurance, as it enables complete traceability of user interactions. For this purpose, MERLIC 26.03 provides an open interface through which activities such as parameter changes or user logins can be automatically transmitted to existing observability or audit systems. In this way, even strict compliance and quality requirements in highly regulated production environments can easily be met.

Another current topic in automation is the EU Cyber Resilience Act (CRA), which will come into force gradually starting in September 2026. MVTec is already developing its software products in compliance with the CRA and supports its customers with questions related to the regulation.

Software framework as a foundation

MVTec is responding to the wide range of requirements and challenges by further developing MERLIC into a software framework. Such a structured programming framework enables rapid development cycles, short time to market, and high stability. A framework paves the way for scalable standard solutions that grow with requirements. It reduces maintenance effort and training requirements, thereby lowering operating costs.

In modern aircraft production, precision is everything. Every hole and every fixing point must be precisely positioned to ensure safety and quality. As part of the DiCADeMA project (Digital Cabin Architectures and Design for Manufacturing) led by the German Aerospace Centre (DLR), a novel, fully digitally networked process has been developed.

Through intelligent automation, this approach elevates aircraft cabin manufacturing to a new level. A key component in this process is an Ensenso 3D camera from IDS Imaging Development Systems, which ensures highly precise detection and alignment of drilling positions.

Digital process chain from design to production

The aim of the project is to establish a continuous digital thread from design to production. Changes to the cabin design, such as seat spacing and the associated new position of the luggage compartments, are recorded directly in the digital design data and automatically transferred to production planning. Simulations allow these variants to be validated before any physical component is manufactured. Once digital validation is complete, production can begin immediately.

To make this digital process tangible, an automated system for marking drilling positions was developed on a mock-up of an aircraft frame structure. Several networked systems work together in this setup: An autonomous mobile robot (AMR) approaches the frame and positions itself near the target area. Mounted on the AMR is a lightweight robot that moves the marking unit, including the 3D camera, into the acquisition position. At this point, the Ensenso camera takes over the fine alignment. An integrated Manufacturing Execution System (MES) controls all sub-processes.

The role of the 3D camera

The camera used, an Ensenso N36, captures the environment as a three-dimensional point cloud and matches it against the CAD data of the aircraft frame. In this way, even the smallest deviations between the target model and the actual geometry can be detected. The system uses this data to calculate precise correction values, which are transmitted to the higher-level MES.

Communication takes place via a standardised OPC UA interface, ensuring reliable and secure data exchange between the camera, the robot and the control system. The MES translates the acquired data into concrete control commands for the robot, which then performs the marking of the drilling position.

The autonomous robot achieves a positioning accuracy of around five millimetres. This allows the camera to reach the acquisition position without risk of collision.

The Ensenso camera becomes a key link between digital design and real-world manufacturing: It recognises local geometries, in this case several rivets and the surface on which they are set and compares the captured point clouds with the reference data from the CAD. This comparison is made possible, among other things, by hand–eye calibration and an iterative minimisation process. The result is a transformation matrix that precisely describes the correction required for the drilling position. By applying this correction value, the drilling position can be set precisely.

An operator follows the vehicle and drills the hole immediately afterwards at the marked spot. This process is repeated for each installation point, while robots and humans can work safely in close proximity to one another.

For this application in aircraft manufacturing, a compact camera with a very short working distance is required in order to keep the path from the acquisition position to the drilling position as short as possible. This helps to maintain high accuracy and avoids excessive robot movements. The Ensenso N36 meets these requirements. The Ensenso N series has been specially developed for use in demanding environmental conditions.

Thanks to its compact design, the camera can be installed in a space-saving manner, either in a fixed position or mounted on a robot arm. This makes it equally suitable for 3D capture of both moving and stationary objects. The integrated projector ensures high-contrast texture even under challenging lighting conditions: It projects additional structures onto the object surface using a pattern mask with a random dot pattern, thereby supplementing missing or weak features. All cameras are pre-calibrated at the factory and can therefore be put into operation quickly and easily.

Benefits for manufacturing

The digital process offers the DLR several advantages. Camera-based alignment significantly increases precision and repeatability. At the same time, continuous data acquisition enables complete documentation and traceability of all process steps. Assembly personnel are relieved, as the robot takes over the time-consuming task of position determination, allowing skilled workers to focus on the actual assembly operation. In addition, production times are significantly reduced, as manual measurements or readjustments are no longer necessary.

The demonstration on the mock-up clearly illustrates the potential that lies in combining the digital process chain, robotics and 3D image processing. In further project steps, the accuracy of the system and the performance of the evaluation algorithms will be examined in greater detail. This will involve not only the camera itself, but also the optimisation of the mathematical methods used to align nominal and actual point clouds.

What is currently being tested in aircraft manufacturing may also be applied in other industries in the future. The system impressively demonstrates how optical sensor technology and intelligent software are paving the way for a new era in manufacturing: networked, efficient and precisely on target.

Visit the IDS website for more information

See all stories for IDS

At the same time, Delta ensures robust protection for customers across a wide range of industries, from machinery and food and beverage to logistics, with robust, industry-leading cybersecurity.

Michael Mayer-Rosa, Senior Director Industrial Automation Business Group EMEA, stated: “Delta’s industrial automation solutions have a proven track record of delivering measurable competitive advantage in fast moving, dynamic market sectors. They enable customers with the agility to adapt efficiently to shifting market demands, economic pressures, and emerging growth opportunities. At the same time, their advanced security features ensure operational continuity, safeguarding manufacturers and supply chain operations against an increasingly complex threat landscape.”

At Hannover Messe, Delta showcased real-world applications of its solutions, including:

Delta 3D ToF Smart Camera: Enables accurate 3D data acquisition and reliable object detection for industrial automation. Utilizing Time-of-Flight (ToF) technology, it captures high-speed 3D information at up to 60 fps, delivering precise depth and position data. Through point cloud processing, the system provides accurate object coordinates, enabling seamless integration with robotic arms for efficient and precise pick-and-place applications. A live demonstration with a SCARA robot at the exhibition will showcase how the solution enhances accuracy and efficiency in automated operations.

Delta Collaborative Robot Solutions: Delta will showcase collaborative robot applications that demonstrate flexible and efficient automation within connected production and material flow environments. Its advanced palletizing system, powered by the DC16 collaborative robot, delivers seamless end-of-line automation. With a 16 kg payload, extended reach, and high precision, the DC16 enables efficient handling of boxes and materials in palletising tasks Integrated with Delta’s ecosystem of components, including vacuum grippers and linear axes, the system forms a fully synchronized, plug-and-play setup that can be deployed quickly without complex programming. Built-in Reflex Safety, collaborative functionality, and a robust IP66 design ensure safe human-robot interaction and reliable operation in demanding industrial environments.

Delta Multi-Drive MX300 Series: Delta introduces its new Compact Multi-Drive MX300 Series, designed to deliver greater flexibility and space efficiency in modern production environments. Featuring a modular multi-axis architecture, the system allows users to configure drive setups according to specific application requirements. Its compact, parallel mounting design optimizes cabinet space, simplifies installation and commissioning, and enables easy system integration. By reducing complexity in wiring and system configuration, the MX300 Series helps streamline machine design and supports more efficient and scalable production operations.

Cyber Security: Delta’s comprehensive cybersecurity solutions have been designed specifically for industrial machinery manufacturers. Beyond ensuring EU CRA compliance and delivering products built with a “Security-by-Design” philosophy, three specialised services are offered to protect Delta’s customers’ machines and businesses: Cybersecurity Assessment, including vulnerability, fuzz, and penetration testing; Compliance Assessment, where customers are guided through Machinery Regulation, EU Cyber Resilience Act and IEC 62443 requirements; and Delta’s Security Concept Design service, where Delta works side by side with its customers to define the technical requirements that best fit their needs. Delta’s mission is simple; to help manufacturers build cyber-resilient machines, achieve regulatory confidence, and ensure operational continuity in today’s rapidly evolving threat landscape.

Founded in London in 2019 with just four members of staff, Recycleye has grown to become the European leader in AI/robotic waste picking technology, helping to revolutionise the waste sector by automating the detection and sorting of mixed recyclables. As a strategic partner, FANUC has been instrumental to the company’s rapid success by helping to derisk Recycleye’s offering to the market. In 2024, the relationship was officially recognised when Recycleye won a FANUC Global Partner Award for Innovation.

The announcement that San Diego-based CP Group has acquired a majority stake in Recycleye significantly expands CP Group’s AI-driven sorting capabilities while further enabling MRF operators to increase recovery, improve purity and generate valuable operational data.

“The combined organisation accelerates AI-enabled sorting and plant control across the full MRF, delivering the performance and purity levels that define the next generation of material recovery,” said Terry Schneider, CP Group CEO. “The applications for AI-based capabilities are significant in MRF systems, and the Recycleye team will enable us to bring powerful new capabilities to the industry in the months ahead.”

Recycleye’s offering combines FANUC’s 6-axis LR Mate robots and iRPickTool visual line tracking technology with its own AI-driven vision system. The Recycleye Robotics solution increases sorting accuracy by up to 12% and improves line output by up to 10%, helping waste operators to boost their bottom line and providing a solution to ongoing labour shortages in the waste management industry. FANUC has supported Recycleye through a commercial and technical partnership since its early days as a startup through to its position today as part of the internationally renowned CP Group.

“This announcement represents a major milestone in Recycleye’s journey, and we are proud to have supported them in creating a product that fits the needs of European and US markets,” said Oliver Selby, Head of Sales for FANUC UK. “Recycleye was our first experience of working with a VC-funded startup. Since then, we have gone on to form strong technical partnerships with a number of venture capital firms, helping both ourselves and those VCs to reduce risk, whilst supporting new entrants into the market. We look forward to seeing what this next chapter will bring for Recycleye, and for the wider recycling sector.”

Visit the FANUC website for more information

See all stories for FANUC

Like many other industries, the woodworking sector faces a variety of challenges. These include quality assurance, untapped efficiency potential, and a shortage of skilled workers. One possible response is further automation. Automation can reduce errors, improve quality, and increase efficiency. In addition, production can be increased and accelerated because machines can operate 24/7 and perform quality control faster and more precisely than humans. Finally, the increasingly scarce human resources can be deployed more purposefully by automating monotonous and physically demanding tasks.

HOMAG Bohrsysteme has developed an automated solution that addresses these challenges. The company is part of the HOMAG Group and provides customers in the woodworking industry with a wide range of support options through its high-tech machines and systems. Its product portfolio includes CNC machining centres, through-feed drilling machines, drilling and dowel-insertion machines, as well as machines for drilling and fitting insertion technology.

The newly developed solution focuses on fully automated loading of a vertical CNC machining centre. At the literal centre of the system is a robot that picks wooden workpieces from a stack, feeds them into the CNC machine, and removes and places them after processing. The key feature is that the workpieces are all individual and their shape and size are not known in advance. In addition, they are arranged chaotically on the stack. Furthermore, not only are the workpieces different from one another, but each must also be drilled individually. The relevant information is stored in a barcode on the workpiece.

Machine vision enables processing to take place completely autonomously despite these challenges. With the help of the machine vision software MVTec HALCON, the robot can recognise the different workpieces and grasp them safely. The software executes numerous algorithms and also reads the barcode information on the workpieces, forwarding it to the CNC machine. Based on this information, the required, different drilling operations are carried out.

Fully automating a labour-intensive process step

Such a fully automated cell developed by HOMAG is in operation at the carpentry workshop of MAB Möbel AG. The company from Muotathal, Switzerland, has been producing quality furniture since 1951 based on ecological and design-oriented principles.

“We want to continue developing with solutions that truly make sense. The further development of the cell with laser scanning and chaotic stacking was the function we had been waiting for. This allows the cell to meet our goal of batch size 1 production – and only then does automation make sense for us,” explains Luca Zingg, member of the management board responsible for corporate development at MAB.

Until now, an employee handled the loading of the CNC machining centre. This involved picking up the workpieces, scanning the attached barcode, placing them into the CNC machine, and depositing them on another pallet after processing. After several hours, this monotonous task becomes physically demanding and is not particularly efficient in terms of profitability.

Tobias Schwarz, Senior Director Product Development at HOMAG Bohrsysteme, explains the goal of the automation: “MAB has set itself the objective of increasing productivity, deploying employees more effectively – and above all in less physically demanding workplaces – and thereby reducing costs.

Another advantage of a fully automated production process is that the workpieces no longer need to be sorted before processing, since the application can also handle chaotically arranged stacks. This saves time in the upstream process step, which further increases productivity.”

The challenge during implementation was to develop a completely new solution, as nothing like this previously existed on the market. The task is also not easy for the machine vision system. This is due, firstly, to the enormous variety of workpieces – different surface decors must also be processed. Secondly, the image processing must function under ambient light. Because not every area is fully illuminated, less powerful vision systems may have difficulty determining the exact position of the workpieces. Finally, it is technically demanding to separate the surfaces of relatively flat boards.

“Despite these challenges, it was clear that such a fully automated solution had to be based on machine vision. We had to teach the robot to see. With other technologies, such as sensors, practical implementation would be virtually impossible – particularly in terms of speed,” explains Schwarz.

Enabling the robot to recognise individual workpieces

The application consists of several hardware components. At its core is a six-axis robot. A vacuum surface gripper system is used as an end effector. A 3D laser scanner is also mounted on the robot’s gripper arm. The drilling operations take place in the DRILLTEQ V-310 CNC machining centre from HOMAG. The machining centre offers a wide range of options for precise processing of wooden workpieces.

For the machine vision software, HOMAG chose MVTec HALCON. “We have been working with MVTec’s software for some time. HALCON has a huge pool of machine vision operators that allow virtually all machine vision applications to be implemented robustly. In addition, the software is flexible when it comes to combining different hardware components. And if technical questions arise, you can simply contact MVTec’s customer service,” explains Schwarz regarding the decision.

At MAB, the production process proceeds as follows: An employee places wooden workpieces onto an unknown and chaotic stack in the work area. The robot then moves over the stack so that the 3D laser scanner can scan it from above. The laser scanner then creates a 3D point cloud – a highly precise three-dimensional representation of objects consisting of numerous individual data points.

After image acquisition, the machine vision software MVTec HALCON extracts the top layer of wooden workpieces from the 3D point cloud and determines the spatial position of each individual workpiece. A stacking algorithm then calculates the optimal order in which the robot should remove the workpieces. This is an important detail because an unevenly unloaded stack could collapse. The robot then begins its work, removing the wooden workpieces according to the calculated order and transferring them to the CNC machining center. Before this, the 3D laser scanner captures a 2D image of the code. MVTec HALCON reads the code and transmits the information to the machine.

The workpiece is then processed according to this information. Afterward, the robot picks up the workpiece again and places it on the target stack.

Multiple image processing tasks

“We are seeing machine vision becoming increasingly popular in the woodworking industry and among carpentry workshops. Our software, MVTec HALCON, offers numerous methods – for example for inspection tasks or for collaboration with robots – that can sustainably support automation and digitalisation in this sector,” says Jan Gärtner, Product Manager HALCON at MVTec.

For the robot in the MAB system to work autonomously and grasp the workpieces precisely, the machine vision software must perform several tasks. First, MVTec HALCON converts the 3D point cloud into information for further processing. For this purpose, HALCON uses 3D object models. This central container forms the starting point for creating a coordinate system within the machine vision software, which is then transmitted to the robot.

Various HALCON operators first determine the distance from the gripper to the pallet, then calculate the top layer of workpieces, and finally determine the precise position of each individual workpiece. These positions are integrated into the coordinate system of the HALCON machine vision software and transferred to the robot.

During the 3D scanner’s capture of the top layer of the pallet, it also records 2D images. HALCON uses these images to read the information from the barcode attached to each workpiece. The challenge here is that the captured image is quite large, while the barcode region is correspondingly small. Reading such small barcodes is a major challenge for any industrial image processing software.

“The image-processing part of the implementation was not entirely trivial. Because of the flat boards, we had to combine 2D and 3D methods. This was possible with HALCON and significantly simplified the implementation,” explains Schwarz.

The system went into operation at MAB Möbel AG in summer 2025. “Thanks to the close coordination with the partners involved, we were able to achieve very good results right from commissioning. The system is now operating very reliably, which makes us very satisfied and gives us confidence for the future,” explains Luca Zingg.

“The increased level of automation significantly relieves MAB, as the employees who previously carried out this task can now focus on other, more important activities. At the same time, this solution represents an important development for us, because it allows us to significantly increase the automation level of our core machines and thus offer customers additional added value,” adds Tobias Schwarz, continuing: “Machine vision plays an important role here, because the technology acts as an automation enabler. In our collaboration with MVTec, we see the opportunity to offer our customers first-class and reliable solutions.”

This makes it suitable for applications such as logistics, automation and robotics, where precise 3D data is required at real-world process speeds.

The Nion captures moving objects with virtually no blurring. Its high resistance to stray light ensures reproducible measurement results both indoors and outdoors. The measuring range of 0.3 to 7.5 metres covers typical industrial scenarios. The robust IP67-rated housing allows it to be used in more demanding environments. Power over Ethernet (PoE) reduces installation effort and cabling.

Patrick Schick, Product Manager for 3DVision and Imaging Software at IDS, says: “The Nion provides stable depth data even under variable lighting conditions. This provides a solid foundation for automation processes that rely on fast and accurate 3D data.”

Compared to standard ToF cameras on the market, the onsemi AR0130 depth sensor offers higher resolution, lower noise, more stable results in ambient light and improved motion stability. This enables the Nion to achieve high depth accuracy even when objects are moving quickly and under variable lighting conditions.

Thanks to its compact design, high measurement quality and excellent value for money, the Nion offers a straightforward introduction to 3D image processing. Companies can integrate the camera flexibly into existing systems and benefit from a cost-effective solution for reliable depth data. “In many cases, existing 2D processes can be retained and supplemented with depth data where necessary, if this aids decision-making within the process,” emphasises Patrick Schick.

Visit the IDS website for more information

See all stories for IDS

The food industry is experiencing a transformative shift in quality control, due in part to advances in artificial intelligence (AI). When combined with rule-based machine vision, AI is enabling automation of processes that were previously impossible, unlocking new levels of productivity and quality assurance.

Cheese consumption is booming globally, and producers are facing increasing challenges as they scale production. Labour shortages, particularly in Europe, are pushing dairies to adopt automation to increase efficiency. Meanwhile, sustainability is becoming a central concern, with an increased focus on reducing waste and conserving resources. Additionally, consumers are demanding higher-quality products with more variety, further intensifying pressure on producers.

As Eberle’s Machine Vision Engineer, Dorian Kopfle, explains: “The cheese-ripening process, which can last up to 14 months, requires constant monitoring to avoid mold and ensure quality. Manually inspecting thousands of cheese wheels is virtually impossible, which is why Gebr. Baldauf, a traditional dairy, turned to us for an automated solution.”

Automation with machine vision and AI

Gebr. Baldauf, located in the Allgau region, commissioned Eberle to solve these challenges. The result is a fully automated monitoring system, that combines a mobile care robot, cameras, and onboard image processing.

The process begins with the inspection of cheese wheels for defects, such as mold spots or blemishes. A 4K camera captures high-resolution images, which are analysed using advanced machine-vision algorithms from MVTec HALCON. The software uses deep-learning methods to detect anomalies earlier, minimising process deviations and waste. The data is stored and made available via a web interface, enabling remote monitoring and control. Simultaneously, the mobile care robot performs its task of treating the cheese wheels, ensuring proper rind formation and removal of unwanted smear layers.

This system not only increases efficiency by reducing manual inspection but also improves the consistency and quality of the final product.

Key outcomes and business impact

The deployment of this automated system has provided several key benefits for Gebr. Baldauf, including:

• Increased efficiency: The mobile care robot operates autonomously, reducing manual labour while ensuring that each cheese wheel is inspected and treated thoroughly.
• Waste reduction: Early detection of mold or defects allows for timely intervention, preventing rejected cheese and minimising waste.
• Improved quality control: The system ensures more consistent and less subjective inspection results by replacing manual methods with AI. As a result, the process achieves a 100% inspection rate, applying the same inspection criteria throughout.
• Full traceability: The integration of industrial image processing ensures complete product traceability. All inspection results are stored digitally for easy access, enabling better decision-making and long-term process optimisation.

Overcoming technical challenges with AI

A significant challenge in developing this system was the natural variability of cheese. Every wheel looks different and undergoes significant changes during the ripening process, which makes rule-based machine vision methods less effective. To overcome this, Eberle utilized AI and deep learning to create a system that could adapt to the unique characteristics of each cheese wheel.

The MVTec HALCON software was instrumental in this process. By training a deep-learning network with a large dataset of cheese images, the system is able to reliably detect defects such as cracks, mold, and discoloration, while ignoring the natural variations inherent to the process. This technology ensures that even subtle anomalies are spotted, allowing for earlier intervention and better quality control.

Eberle’s goal was not only to automate the inspection process, but to fully integrate AI into the cheese-ripening workflow. Currently, the system is capable of performing real-time inspections and autonomous care, with minimal human involvement. However, the company is working on refining the system further to handle all types of cheese and stages of ripening, with the long-term goal of creating a fully automated, AI-driven system that requires no human input.

The system also provides a solid foundation for future digitalisation efforts, with the potential for integration into larger digital platforms, such as ERP systems and the cloud, to further optimise the production process.

Scaling and further digitalisation

Building on the success of this project, Eberle is now focused on scaling the solution to meet the needs of the entire cheese industry. The company plans to standardise the system and integrate it into both mobile and stationary care robots for cheese production worldwide.

Furthermore, the system’s AI capabilities are continually evolving. Eberle aims to refine the deep-learning models to handle different cheese types and ripening stages, enabling fully automated classification and inspection. This will allow producers to further reduce human involvement while maintaining the highest standards of quality.

As Christoph Muxel of Eberle summarises, “Our machine vision-based solution demonstrates how automation can sustainably improve quality, efficiency, and competitiveness in the food industry. This project is just the beginning, and we’re excited to take these innovations to a global scale.”

In this context, the Tekniker technology centre, member of the Basque Research and Technology Alliance (BRTA) partnership, with extensive expertise in this set of technologies, will present a solution that brings together automation, high-precision measurement and digitalisation in industrial environments at the next edition of the Biennial International Machine Tool Exhibition (BIEMH).

The demonstrator, developed in collaboration with ZEISS, KUKA and SCHUNK, will consist of a robotic system capable of automatically identifying, collecting, positioning and measuring parts with almost identical geometries. This robotic measurement allows for quality control of the parts and classification according to their reference and conformity.

“The main differential element is the combination of a flexible component feed with advances in digital metrology that allow fully automated quality control, integrating visualisation, handling, measurement and classification into a single system. This approach is not common in industrial environments and is an innovative and advanced solution,” highlights Gorka Kortaberria, director of Industrial Metrology at Tekniker.

The solution is mainly aimed at advanced manufacturing applications in sectors such as automotive, aeronautics, energy or precision component manufacturing.

Consolidated technologies

The prototype developed by Tekniker combines consolidated commercial technologies with in-house developments in integration, robotics, control and machine vision.

To the solution, ZEISS adds its DuraMax measuring system, which is specifically designed for demanding production environments and offers high precision, even in changeable conditions. For its part, KUKA brings a 7-axis collaborative robotic arm designed for precise and safe handling in environments shared with people. And SCHUNK includes a series of systems that allow parts to be secured and handled reliably during the measurement process.

This technological combination is completed with Tekniker’s Smart Picking asset, which makes it possible to locate and manipulate parts in unstructured environments.

“Our application allows the system to determine the position and orientation of parts from information obtained through machine vision, and then guide the robot towards the parts it needs to handle,” adds Eneko Ugalde, director of Intelligent Autonomous Systems at Tekniker.

Finally, the centre also incorporates its capabilities in plant and process digitisation through its Smart Factory Hub software, highlighting the management of critical data from production operations and being able to learn from them for subsequent decision-making.

The solution will be on display from the 2-6 March at the BIEMH 2026 Tekniker stand, located in pavilion 1, aisle E24.

At Machine Building Live, IDS highlighted everything from open modules to fully embedded inspection systems, with a live demonstration of object detection using AI. Also on show was a live streaming camera for use within a machine to record faults and events, which can be downloaded subsequently for analysis.

A further demonstration highlighted IDS’ capability in 3D imaging for applications such as robot pick and place, as well as in the medical industry in areas such as MRI scanners.

Visit the IDS website for more information

See all stories for IDS