Industrial Image Processing
Image processing systems allow machines to see via industrial digital cameras and highly developed software algorithms. This opens up fascinating new possibilities for automation.
Quality and output are increased through advantageously applied camera technology combined with robot and servo drive technology. Digitization allows for seamless traceability.
When it comes to controlling the existence and completeness of work pieces, industrial camera systems are in action tirelessly. Today, vision technology also provides reliable support for object measurement and surface inspection.
In contrast to the human eye, digital image processing allows a permanent storage of image data and thus a backtracking of quality. In this case, the camera is superior to the human eye.
Image processing systems are successfully used in quality management. Following recurring patterns, the quality of products is measured and assessed through nondestructive testing.
A high degree of rationalization and consistent quality are achieved by automatic object measurement.
Cheese quality control
One example of such a solution is a fully automated system comprising a mobile maintenance robot and industrial image processing. This solution reduces the wastage of cheese wheels during the maturing process, improves quality and cuts costs. The combination of AI with industrial image processing enables increased productivity in the field of cheese quality control, particularly in quality assurance.
The solution comprises a care robot equipped with bar lighting and a 4K colour line scan camera. A compact industrial PC is used as the hardware, whilst a central computer at the customer’s site handles the deep learning-based classification. The MVTec HALCON software for industrial image processing is used in conjunction with our own ‘Storage’ software to monitor and document the care process.
Before each care process carried out by the robot, the cheese wheels are inspected for defects such as mould spores using machine vision. The images captured by the camera are analysed by the software. The results are stored in a database accessible via a web interface, enabling the customer to identify defective cheese wheels at an early stage and adjust the care process accordingly. At the same time, the mobile robot carries out the care tasks by brushing the cheese wheels and treating them with care fluids to control rind formation and remove unwanted slime layers.
The mobile robot moves through the cheese cellar and processes the cheese wheels in groups of three, each resting on a board. An image is captured for each set. After pre-processing, the image is sent to the customer’s central computer, where it is classified using deep learning. In addition, the position data of the cheese wheels is transmitted to determine the type of cheese and a unique cheese ID. This data, along with the analysis, is accessible to the customer via the warehouse management system.
Object Recognition
In many areas of automation, digital industrial cameras help identify objects. The identification of components takes place via shape and appearance or via a coding system.
The use of such systems is not tied to a certain position and often takes place in ongoing production processes.
A special application is the recognition and tracking of moving objects. This requires a high error tolerance of the control system. A working example is the remote control of robots by human gestures.
Camera systems are a fixed component in our automation solutions. We use the technology consistently to automate operational procedures. For this, we rely on our own in-house developments.
Through gesture control, we combine human fine motor skills with the power and capacity of a machine.
Surface Inspection
Camera applications are ideal for inspecting surfaces. The system automatically checks the condition of surfaces for predefined quality characteristics.
The fitting technology is chosen according to the requirements. Cameras scan the surface in either 2D or 3D. The control system evaluates the measured data and further processes them.
We use inline systems for inspection in high quality requirements on production lines.
With 3D scanning technology, we achieve high accuracy and reproducibility.
Assistance Systems
Assistance systems are used in applications where there is no insight into detailed process sequences, or when accuracy is required over a long distance.
Assistance systems are digital colleagues with a supporting role. The brand new technology “Augmented Reality” reflects digital information into reality.
These systems extend human perception and support, for example, the assessment of dangerous situations.
We are very successfully using assistance systems in lifting technology. The camera reliably spots in advance, what the human eye cannot capture from its perspective. The information, which is processed and then projected with actual data supplements the perception of man.
Object Measurement
Object measurement is about precise shape and size accuracy. The data capture is carried out with high-resolution 3D camera systems. The software automatically compares the 3D scan with the specifications from the CAD model.
For example, we use digital object measurement for automatic quality control. The quality assessment is fully automated using the CAD model.