Labour saving 3D vision solution for chocolates

Scorpion Vision has developed a sophisticated 3D stereo vision-based inspection solution that ensures perfect presentation for chocolate gifting trays. By performing with near 100% accuracy a task that is usually carried out by one or two humans, Scorpion’s system can help confectionery manufacturers and packers to combat unskilled labour shortages, whilst increasing line efficiency.

This system deploys the Scorpion 3D Venom camera to inspect chocolates that have been deposited in compartmentalised trays by pick and place robots. Occasionally, after being placed, chocolates will bounce up and either turn upside down or jump out of the tray altogether.

Scorpion has engineered an advanced vision solution that images the chocolates in 3D and takes precision shape measurements to confirm that each chocolate is in the right compartment and position. At the heart of the solution is the global shutter Scorpion 3D Venom camera, which is ideal for applications in cutting-edge 3D stereo vision systems owing to its short baseline.

Paul Wilson, managing director at Scorpion Vision, explains: “The shorter the baseline, the more accurate the stereo or ‘z’ depth – a camera trait that is essential for reliable decision making in this application.

“The system requires several data sets to determine, with high accuracy, whether the right chocolate is in the right position. As well as generating a 3D profile, it relies on precise dimensional measurements, 2D imaging and colour imaging to build a complete and detailed picture. With this data combination, it can even analyse the texture of each chocolate to determine whether they are correctly placed. If a chocolate is upside down, for example, the vision system recognises that the texture or pattern on that chocolate is different to the reference.”

Without this system, factories usually have to build an inline buffer system into their process and deploy manual labour to perform quality checks of chocolate trays. This arrangement generally requires at least two people who have to move quickly to reseat chocolates as they pass down the line. With an automated inspection system, any packages are diverted off the line so they can be reworked offline. This eliminates bottlenecks and back-ups, and, most importantly, guarantees perfect tray presentation.

This solution was originally engineered with chocolate manufacturing in mind but could just as easily be applied on any production line where compartmentalised presentation trays are used – from cup cakes, patisserie items and pastries to biscuit selections. It is also possible to overlay this solution with AI for enhanced performance and reliability.

“We create a profile of the product in 3D and analyse it for certain reference features. We then use AI to enhance extraction of these features – essentially training the vision system to identify and locate anomalies. The application of AI makes texture and pattern verification easier to do and even more reliable than with the use of 3D vision alone,” says Paul.

This application is a great example of Scorpion’s ability to harness its vision knowledge to solve production problems. Paul adds: “As well as drawing on the wealth of technology that exists within Scorpion, we have curated an extensive toolbox of machine vision components and software products from selected manufacturers whose technology we admire. We know what each and every one of these products can do and our strength lies in choosing which ‘building blocks’ to use for a specific application, and integrating them into seamless, line-ready solutions.”

Visit the Scorpion Vision website for more information

See all stories for Scorpion Vision