Vision and Automation Solutions for Engineers and Integrators Worldwide
Responding to a corporate goal to be environmentally sensitive
Nestlé HealthScience decided to change the color of measuring scoops (from red or green to transparent) included in cardboard canisters
“The colored scoops are very hard to recycle because of the colored pigments,” explains Klaus Keitel
national account manager for strategic customers at SICK (Waldkirch
which designed an AI-enabled machine vision system for Nestlé (Vevey
But the color change had an unintended effect on the automated inspection process at the company’s manufacturing plant in Osthofen
where the nutritional supplement is produced: The automated inspection system could no longer verify the presence of the scoops in the cardboard canisters
plant managers assigned an employee on each shift to the task of watching the process and pulling canisters without scoops from the line
it was a hard job,” explains Armando Simoni
a technician focused on measurement and project management at the company’s plant in Osthofen
Nestlé opted to replace the machine vision system with the new one from SICK
which uses deep learning algorithms to detect the transparent scoops
a measuring scoop drops from 20 cm above the production line into an empty canister
so that the scoop ends up near the top of the can
After the presence of the scoop is verified
This happens at a rate of between 40 and 80 canisters per minute
About 13 different adult nutrition products—different formulas and can sizes—are produced on a rotating basis on a single line at the plant
the old machine vision camera system snapped an image right after the scoop was added
It would then count the colored pixels in the image to determine if the scoop was present
This process worked fine with a colored scoop
But this was not the case with the transparent scoop because the gray aluminum seal
which is what the consumer removes to access the powder
reflected onto the transparent plastic of the scoop
the camera system couldn’t distinguish between the scoop and aluminum seal
“The classical vision system could only count whether it's a dark or it's a white pixel,” Keitel explains
Once Nestlé decided to replace the vision system
plant managers reached out to numerous machine vision companies for proposals
Most of the companies quoted a 90% accuracy rate
while SICK’s sales representatives said their system would achieve a 99% rate by using algorithms enabled with AI
The food and nutrition company’s RFP was challenging for a variety of reasons
Nestlé went through a transition period in which it used both colored and transparent scoops because it wanted to deplete its inventory of the old scoops
Nestle’s plant managers wanted to transition from filling one type of container to the next on the production line without adjusting settings on the camera
Work began on design and testing of the SICK system in April 2021; it has been operating in a production capacity since June 2022
Related: Deep Learning/AI System Provides 100% Inspection for Food Producer
To design a system that can detect the presence of the transparent scoop
SICK incorporated deep learning algorithms with a monochrome 2D snapshot camera
which is a global shutter CMOS camera with a C-mount lens mount
The camera is compatible with the GigE interface for video and data transmission over Ethernet networks
so it can snap images of the canisters after the scoop is added
The line is illuminated with a rectangular LED backlight from planistar Lichttechnik GmbH (Himmelstadt
Now that the algorithms have been developed for this application
Simoni can modify them as necessary to accommodate changes in canisters or scoops
the algorithm determines whether a scoop is present
which transmits the result to a PLC from Siemens (Munich
It usually takes about 50 milliseconds for the camera to produce a result and send it to the PLC
The PLC is in a control cabinet near the station where the canisters are filled with the powdered supplement
A 5 m 12-wire cable attaches the camera from SICK to the PLC
Related: Optimizing Machine Vision Lighting for Food and Beverage Inspection
As is typically the case with deep learning algorithms
their performance in a production environment depends on how well they are trained
Simoni says Nestlé and SICK learned this lesson while implementing the new machine vision system
The employees from SICK and Nestlé involved in the project did not get the results they wanted after a first round of training
they added images of scoops in a variety of orientations
as the exact position of a scoop depends on how well the canister is lined up under the automated mechanism when the scoop drops from above
so the position of the canisters can vary
They also realized that they needed two neural networks to accommodate the different canister sizes: one for those with diameters of 73 or 99 mm
and a second neural network for canisters with diameters of 140 mm
the plant managers at Nestlé added an automated mechanism to push canisters without scoops off the production line
the SICK system sent a signal to the PLC to stop the line if it detected a canister without a scoop
the camera software detected it and then sent a signal to the PLC to restart the line
Simoni says the new system is more efficient because it solves the missing scoop problem without halting production
because it identifies canisters without scoops with nearly 100% accuracy
Linda Wilson joined the team at Vision Systems Design in 2022
She has more than 25 years of experience in B2B publishing and has written for numerous publications
she was the senior editor at Medical Laboratory Observer
The death of a student posed a mystery for the Münster duo Thiel and Boerne: a fellow student was convinced that she was the perpetrator
A well-intentioned joke by forensic scientist Professor Karl-Friedrich Boerne(Jan Josef Liefers) put his relationship with Chief Inspector Frank Thiel (Axel Prahl) to the test in the 47th Münster"Tatort: Fiderallala" (script: Regine Bielefeldt)
At the same time, the death of a student puzzled the duo in the new "Tatort":
Although a fellow student seemed rock-solidly convinced that she was responsible
her account of the crime did not match the injuries to the corpse
It turned out that her memory had been manipulated
In order to lure his frozen pizza-crazy colleague to a student party
Boerne invented a corpse without further ado in the crime thriller directed by Isa Prahl
The plan worked: Thiel enjoyed himself at the party
while Boerne not only consumed plenty of THC and alcohol
but also landed a hit on the net with his intoxicated rendition of the "Bird Wedding"
Driven by offended pride, Boerne terminated Thiel' s tenancy as punishment for not intervening
which the professor ultimately wanted to eradicate by blowing up Thiel's letterbox
The bickering between the two main characters was just an entertaining side skirmish to the actual case to be solved:
Student Chris Haffmeister (Jonas Stenzel) died as a result of a mysterious stab wound
The estimated time of death coincided with the student council party
which Thiel and Boerne were also attending
The circle of witnesses and potential perpetrators was correspondingly large
but none of them could remember much about the night of the party
It soon emerged that Chris Haffmeister managed the AStA's room exchange until his death
had initially applied in vain for one of these rooms and was consequently suspected of murder
The inconspicuous student Lucy Osthofen (Luise von Stein)
claimed to be responsible for Chris Haffmeister's death
Boerne wanted to get to the bottom of the matter with a "standard lie detector" - with the result: "Nothing she says can be true
It's as if she has internalized the lie like a truth."
Things got even crazier when a second body was found: Achim Probst was beaten to death in his villa
the former professional footballer Erkan Gül (Surho Sugaipov) confessed to a robbery-murder
But this statement could not be true either
It is indeed possible to manipulate a person's memories
as an experiment by psychologist Aileen Oeberst proves:
"We invited students under the pretext of conducting a study on childhood memories," describes the scientist in an interview with "ZEIT Magazin".
She continues: "We spoke to their parents in advance and obtained real memories
We later mixed these with false claims and asked the test subjects about them
a family vacation in Italy: here we claimed that the test subject had been lost as a child during a trip on this vacation - but that wasn't true."
but the longer she thought about the alleged experience
the more details she added to the story herself
such as the warm weather: "In the interviews
we repeatedly support this false memory by reinforcing it and encouraging them to think further
test subjects can be convinced that they remember it that way," explains Oeberst
In addition to the ability and the motivation to take on board the false memory
what is needed above all are trustworthy people who keep telling the subject this story
this behavior can have fatal consequences: "If a therapist argues that the reason for an illness
is a trauma from the past and wants to 'drill down' into it
It was similar in "Tatort: Fiderallala": therapist Solveig Menke (Adina Vetter) had implanted the false memory of the night of death in her patient Lucy Osthofen in order to protect her own daughter Fraya from being arrested
had been beaten to death by his own son-in-law Dennis Kollberg (Tom Radisch)
who was also being treated by Solveig Menke
When he found out about her manipulative abilities
he blackmailed her into providing him with a false alibi
which the ex-footballer ultimately provided
Thiel and Boerne managed to put their dispute aside at the end of the 90-minute episode
Boerne even promised his tenant a new apartment
It remains to be seen whether the audience will get to see this in the upcoming Münster "Tatort"
What is certain is that the upcoming 48th film will be the last with actress Mechthild Grossmann as public prosecutor Wilhelmine Klemm: The 76-year-old announced her retirement in August 2024
Filming of her farewell episode "The Invention of the Wheel" is scheduled to take place in March and April 2025