Camera-Based Cap Control with Artificial Intelligence

The bottle and beverage industries face the classic dilemma of numerous other industries, strong price pressure combined with high-quality requirements. In a French manufacturer of plastic caps’ quality control department, this is also the case.

Whilst running at high speed on a production line, detecting cracks and micro-cracks on plastic caps reliably in 40 different shades and colors is a real challenge.

With the help of image processing technology and artificial intelligence, APREX Solutions from Nancy, France, has achieved this goal successfully. The basic images are supplied using a USB3 industrial camera from IDS Imaging Development Systems GmbH.

SOLOCAP manufactures all types of plastic caps for the food sector at its industrial site in Contrexéville and is a subsidiary of La Maison Mélan Moutet, "flavor conditioner since 1880.." Among these plastic caps is a top-class screw cap suitable for any PET or glass bottle.

It allows a quick, simple, absolutely tight and secure seal because of a clampable lamella ring arranged around the bottle collar. Yet, the slats must be checked for cracks, tears and twists during production very reliably and extremely carefully. This is the only way to guarantee absolute tightness.

Application

APREX Solutions realized the new solution with artificial intelligence individually on the basis of in-house software algorithms as the previous inspection system could not adhere to these high requirements.

The required specifications were developed in advance in cooperation with the customer. This also included a number of inspection stages, one of which, for instance, was to avoid false reports by having the reject control. The introduction took place in two parts:

First, with the help of the intelligent APREX Track AI solution, the specific ‘SOLOCAP application’ was trained. The software includes a number of object classifiers, detectors and standard techniques which operate at different levels.

They ultimately provide the desired result tailored to the customer when they are networked accordingly. Four control levels with a number of test points guarantee a reliability rate of more than 99.99 %.

The APREX inspection system checks plastic caps for defects running at high speed on a production line.

The APREX inspection system checks plastic caps for defects running at high speed on a production line. Photos: © APREX © Shutterstock

In the second phase, this application was used in the production line straight after the first assembly run with APREX Track C&M. The latter was developed especially for the industrial sector’s diverse image processing needs.

This includes the control and safeguarding of a production line up to the measurement, identification and classification of defects in the production environment, among other things. The software suite provides the desired results quickly and efficiently, with no time-consuming development processes.

The complete system is ready for utilization by the customer after a short training of the AI techniques. The SOLOCAP combines an IDS UI-3280CP-C-HQ industrial camera, a programmable logic controller (PLC) and powerful ring illumination to supply comprehensive control over all inspection processes.

40 different colours and shades are reliably detected.

40 different colours and shades are reliably detected. Photos: © APREX et Shutterstock

It also records all workflows in real-time and ensures complete traceability. Only one camera is required to do this, but APREX TRACK C&M is able to handle up to five cameras.

The difficulty of this project consisted mainly in the very subtle expression of the defects we were looking for and in the multitude of colors. With our software suite, it was possible to quickly set up an image processing application. Despite the complexity.

Romain Baude, Founder, APREX Solutions

The image from the camera supplies the basis for the assessments. It makes the smallest details visible to the software by capturing every single cap directly in the production line at high speed.

One Crucial Component: The Camera

In terms of light sensitivity, color reproduction and dynamic range, the UI-3280CP-C-HQ industrial camera integrated into the system with the 5 MP IMX264 CMOS sensor from Sony sets new standards.

The USB3 industrial camera supplies excellent image quality with an extremely low-noise performance at frame rates of up to 36 fps. CP stands for ‘Compact Power’ this is because the tiny powerhouse for all types of industrial applications is reliable, quick and enables a high data rate of 420 MByte/s with a low CPU load.

Users are able to choose from a wide variety of modern CMOS sensors from manufacturers like CMOSIS, Sony, e2v and ON Semiconductor with a complete spectrum of resolutions.

The camera’s innovative, patented housing design with dimensions of just 29 mm3 makes it suitable for tasks in the fields of automotive, automation, agriculture, medical technology and life sciences, logistics, traffic and transport, to name a few.

A reliable electrical connection is ensured by using screwable cables. The cameras are automatically recognized by the system and are ready for use straight away because of the IDS-characteristic plug & play principle, as Romain Baude confirms:

In choosing the camera, the UI-3280CP-C-HQ’s excellent color reproduction and its high resolution of 5 MP were decisive factors. The model enabled a quick, uncomplicated integration into our system at the same time.

Outlook

Head of Technology and Industry at SOLOCAP, Anthony Vastel, has seen much potential in the new inspection system: "APREX's AI-based approach has opened new doors for our 100 % vision-based quality control. Our requirements for product safety, but also for reject control, especially in the case of false reports, were quickly met. We are convinced that we can go one step further by continuing to increase the efficiency of the system at SOLOCAP and transferring it to other production lines."

AI provides quality assurance but also new, undreamed-of fields of application in all of the other industries where image processing technology is utilized.

Where classic, rule-based image processing reaches its limits, it makes it possible to solve tasks. So, high-quality results can be attained with comparatively low effort - creatively, quickly and efficiently.

IDS and APREX Solutions have recognized this and provide solutions with intelligent products that make it easier for customers to enter this new world. Image processing and AI are the perfect combination on course for growth.

USB 3 uEye CP – Incredibly Fast, Incredibly Reliable, Incredible Sensors

  • Resolution: 5.04 MPixel
  • Dimensions: 29 x 29 x 29 mm
  • Interface: USB 3.0
  • Shutter: Global Shutter
  • Model: UI-3280CP Rev.2
  • Sensor type: CMOS
  • Manufacturer: Sony
  • Frame rate: 36.0 fps
  • Connector: USB 3.0 micro-B, screwable
  • Sensor format: 2.3"
  • Resolution (h x v): 2456 x 2054 px
  • Weight: 50 g
  • Applications: e.g., mechanical engineering, medical technology, industrial image processing, surface inspection, electronics inspection 

Camera-Based Cap Control with Artificial Intelligence

Image Credit: IDS Imaging Development Systems GmbH

Client

For applications in the development, optimization, control and safety of processes in industrial plants, the deep-tech company APREX Solutions develops software and algorithms. The aim is to contribute to the transition to Industry 4.0 by increasing and streamlining the safety of production. 

This information has been sourced, reviewed and adapted from materials provided by IDS Imaging Development Systems GmbH.

For more information on this source, please visit IDS Imaging Development Systems GmbH.

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    IDS Imaging Development Systems GmbH. (2021, June 25). Camera-Based Cap Control with Artificial Intelligence. AZoOptics. Retrieved on September 21, 2021 from https://www.azooptics.com/Article.aspx?ArticleID=1957.

  • MLA

    IDS Imaging Development Systems GmbH. "Camera-Based Cap Control with Artificial Intelligence". AZoOptics. 21 September 2021. <https://www.azooptics.com/Article.aspx?ArticleID=1957>.

  • Chicago

    IDS Imaging Development Systems GmbH. "Camera-Based Cap Control with Artificial Intelligence". AZoOptics. https://www.azooptics.com/Article.aspx?ArticleID=1957. (accessed September 21, 2021).

  • Harvard

    IDS Imaging Development Systems GmbH. 2021. Camera-Based Cap Control with Artificial Intelligence. AZoOptics, viewed 21 September 2021, https://www.azooptics.com/Article.aspx?ArticleID=1957.

Ask A Question

Do you have a question you'd like to ask regarding this article?

Leave your feedback
Submit