Industrial image processing in Schubert packaging machines

The pick & place vision system
for the highest product quality

In manufacturer Guschlbauer’ packaging machine,  the pick & place vision system monitors the quality of the baked goods.

Packaging machines with the modular image processing system

The pick & place vision system ensures consistently high quality

Automation is inconceivable without industrial image processing. Image processing systems also play a major role in automated packaging processes. This is by no means insignificant, because an essential feature of processes such as pick & place or flow-wrapping machines is the continuous flow of product. Cameras, however, work with individual images that cannot fully represent the product flow. This is why Schubert developed its own pick & place vision system, which is tailored to the requirements of packaging machines and supports the use of robotics.

A vision system for quality control

With its pick & place vision system, Schubert customers primarily benefit from automated and highly efficient quality control: Only products that meet the customer’s programmed specifications are recognised by the vision system and then picked up by the packaging machine’s pick & place robots. Whether a flow-wrapping machine, a case packer or simply pick & place – at the end of the packaging process, the manufacturer benefits from fewer rejects, fewer complaints, lower costs and a guarantee of consistently high product quality.

Modular imaging systems for every application

Line sensors are a fundamental component of Schubert’s pick & place vision system. They are integrated into the incident-light scanners and 3D scanners, and enable a continuous product flow to be observed. Like all system components in Schubert packaging machines, the vision system is also modular in design: The 200-millimetre-wide modules can be combined in one scanner up to a working width and therefore a product width of 1800 millimetres. To complete the industrial image processing, the vision system also includes integrated lighting, software and other applications. These include the “reach into the box” feature, where products are picked up from the pile by a robot in pick & place.

The future: Neuronal networks

There are, however, products which cannot be inspected with conventional image processing. This is because classic pick & place vision systems are based on the fact that products can be clearly identified with just a few parameters. In the case of so-called “living” products, which have high production tolerances, the deviations are so great that they are difficult or impossible to describe mathematically. The software would have to check too many parameters, which are also correlated and interdependent. This is why Schubert will rely on neuronal networks and artificial intelligence (AI) for its vision system in the future. The image processing system therefore learns on its own and sorts the products into classes independently in a longer learning process. This means that the parameters are selected by the system and no longer by the programmer. For customers, this means a significant step towards independence: In the future, they could actually use neuronal networks, under certain conditions, to teach their packaging machine to handle a new product on its own.

Modular scanner technology

Image processing with a vision system in 2D and 3D

A pick & place vision system controls Surgital’s frozen ravioli over the entire width of the product line.

Reflected-light scanner 2D for colour and surface inspection

  • Telecentrics: Vertical view of the product without image distortion
  • Precise shape control
  • Precise dimensional control
  • Precise colour control
  • Modular scanner size
In the Bahlsen packaging machine, the pick & place vision system uses 3D scanners to check product quality while controlling a total of 24 pick & place robots.

3D scanner for additional height control

  • Stereoscopy with two adjacent sensors each: Calculation of the individual 3D image segments from two images with different perspectives
  • Light pattern projection onto the product belt: Calculation of the 3D image from deformations of the unique Schubert light pattern
  • Precise height control
  • Precise shape control
  • Precise dimensional control
  • Precise colour control
  • Modular scanner size

Quality control in practice

Pick & place with the vision system

Color check

In manufacturer Pixie Ice Cream’s packaging machine, a pick & place vision system with a reflected-light scanner ensures the correct product combination. The robots automatically pack the coloured ice cream varieties into the boxes as assortments.

Shape check

The long-established Guschlbauer confectionery produces a wide variety of fine baked goods, ranging from punch cubes and coconut domes to wafers and sticks. Before packing them into trays with pick & place, each product is checked for flawless shape by a reflective-light scanner. The trays then run into two flow-wrapping machines.

Height check

At the Bahlsen confectionery manufacturing site, the vision system uses a 3D scanner to adjust the specified product height for the cream-filled biscuits. In the packaging machine, for example, only complete products are processed via pick & place, and the trays are then packaged in a flow-wrapping machine.

The modularly designed pick & place vision system

Ein modular erweiterbarer 3D-Scanner des Vision-Systems von Schubert im unverbauten Zustand.

Scanner modules and a software library for more flexibility

To be able to adapt the image processing system to each product belt, the scanners consist of modules that can be combined. Belt widths of up to 1800 millimetres can be monitored. The software programs are also modular: A digital library comprises various program modules for different product categories. These are specified for each customer.

Format changeover through automatic adjustment of the parameters

The formats of the packaging machine and their associated parameters are stored in the vision system’s ready-to-use software. For this purpose, certain parameters such as height, colour or shape must be assigned to each product based on customer specifications. When the format is changed, the software loads the new format and automatically adjusts the parameters for image recognition.

For picker lines and flow-wrapping machines

The vision system with pick & place

Pick & place packaging is not only about quality control. The position of the products on the product belt is also important information that the vision system recognises. This information is passed on to the pick & place robots. This is the only way the robots are able to precisely control and grip the products. Only flawless products enter the subsequent packaging process.

More about the benefits of the Flowpacker flow-wrapping machine

For pharmaceutical and other applications

The vision system for labels and codes

Especially when packaging pharmaceutical products, it is very important to check the labels that have been glued or printed on. Cameras are used here, which (most often) use flash lighting and a still image during the packaging process to verify each label. The labels are also checked in the case of bottle packers. Another application is the identical alignment of products in an outer packaging.

For pick & place from an unsorted group of products

The vision system for reaching into the box

If a pick & place robot picks products out of a pile, the position of the other products also changes with every pick. With Schubert technology, a 3D camera system is used to fully automatically reach into a box of unsorted complex products. The image processing system’s four cameras and two light pattern projectors precisely detect products of all shapes and colours in position, height and rotation. This enables the robot to pick up the products with absolute accuracy. After each grip, the objects are captured again in three dimensions.

For “reaching into a box”, the pick & place vision system’s four cameras and two light pattern projectors detect the products accurately in terms of position, height and rotation.
Portrait of Dr. Abdelmalek Nasraoui, expert for the Pick and Place Vision System at Schubert

Kontakt

Would you like further information?
Ask our expert!

Dr. Abdelmalek Nasraoui
Research and Development Manager / Machine Vision

Telefon: +49 7951 400-848
E-Mail: a.nasraoui@gerhard-schubert.de