Foreign body and contamination
Dark inclusions and colour deviation, common with recycled content where the baseline moves batch to batch. On food contact this is a safety finding, not a cosmetic one.
Industries
Packaging
Every part checked at line speed, logged by cavity
Packaging runs high cavitation on short cycles. A fault on one cavity is on tens of thousands of units by the end of the shift, and nobody opens the case until it reaches the customer. Deepvis inspects every part and logs every reject against its cavity.
- Every part checked, not one in forty
- Contamination handled as a foreign body finding
- Checks at each step of the packing line, not only at the end
We support the inspection of closures and lids, thin-wall containers, IML pots, trays and heat-sealed packs.
- Black Speck
The defects
Faults a sample plan misses
Real parts off the tool. Drag any frame. The photo is on one side and the same frame marked up on the other, shot at the same exposure.
- Black Speck
Black specks on a closure
Dark inclusions in translucent PP, a few pixels each. On a food contact part this is a foreign body finding, so it goes into the complaint and CAPA process rather than the cosmetic one. It is also the fault an operator on an AQL sample is least likely to catch.
- grey cube
Finding the part
Parts in a bin, every orientation, most of them part-covered. The part has to be located and separated from the ones behind it before anything can be checked on it.
Line control
Check at each step, not only at the end
End of line tells you the pack failed. Checking each step tells you where it failed, and stops you putting film, a weld cycle and a label onto a part that was already scrap.
01
Check the part before packing
Part picked out of the bin. If it is wrong here, everything after it is wasted on it.
- grey cube
02
Check the pack before sealing
Film open, part in place. Last point a bad pack can come off the line without also losing the film, the weld and the label.
- plastic before weld
03
Check the seal and the count
Two packs off one weld. Both checked and both counted, so a short case and a double pack are caught in the same pass.
- plastic after weld
04
Fail the pack, log the reason
Puncture through the film. The pack fails and the hole is logged separately, so the record has the reason next to the result.
- Plastic post heatshrink NOK
- Hole
On the machine
Mounting, cycle time and rejects
Where the camera goes, how fast the result comes back, and what happens to a bad part.
- 01
Camera over the belt, denester or sealer
Wherever the parts already pass. One camera can cover several parts per frame, which suits high cavitation.
- 02
Result inside the cycle
Under 200 ms, so the result is with the part rather than behind it.
- 03
Reject on your limit
You set the limit per class. The result goes out on the line’s IO to a diverter, an air blast or the HMI.
- 04
Every pack logged
Image, cavity, class and size per unit. That is the file a retailer audit or a complaint investigation asks for.
Defect list
What we inspect for
Short shot on closures
Rim or skirt not filled out. On a snap fit that is a seal failure, and a weight check will not catch it.
Flash and stringing on the sealing face
Material where the seal has to make contact. Small enough to pass a visual, big enough to make a leaker.
Seal and weld faults
Puncture or incomplete weld on a finished pack, logged separately from the pass or fail so the reason is on the record.
Cavity drift
One cavity going out while the rest are in. Only visible if rejects carry a cavity number.
Count and presence
Two packs where there should be two. Counted in the same pass as the quality check, so a short case is caught at the sealer instead of at goods-in.
What changes
What changes on the line
Four things a shift notices.
Block the cavity, keep running
A reject with a cavity number means you can shut off one cavity and keep the tool in production, instead of pulling it on a suspicion.
Fewer complaints
A foreign body finding at the customer costs the investigation, the CAPA and often the account. Catching it on the line is the cheap version.
Fewer leakers
Seal faults caught at the sealer instead of at the filler, where a leaking pack takes the line down and the product with it.
Audit file
Audits ask what you check, how often, and what you did about the last finding. Every part inspected and stored covers all three.
The method
How we find them
Four steps, whatever the part is. Everything above was marked up by hand first. That is how the model learns your defects, and the only way it learns them.
You set what counts
We start from your reject criteria, on your parts. The model returns what you marked up and nothing else.
Lighting first
Camera, optics and lighting are picked for the material. Frosted PP and a black closure are different jobs.
About 120 parts
A hundred frames off the running tool, 120 marked up. Your resin, your regrind, your colours, your fixture.
Two hours to a model
Training takes about two hours. After that every part is checked in the cycle and rejected on your limit.
First step
Prove the defects are detectable
You send 100 parts — 50 good, 50 faulty. We photograph them, train a model on them in our lab, and 14 days later you have the report.
What the report contains — click a page
Guarantee
If we cannot find the defect type you point at, you get your money back. Buy the system within 60 days and the fee is credited in full.
Book a detectability analysis
DKK 8,000
FAQ
Frequently Asked Questions
Simple and Easy to deploy AI Inspection Systems for modern production environments.
What types of defects can Deepvis detect?
Deepvis can detect complex and unpredictable defects that are common in recycled plastic, such as black specks, short shots, overmoulding, contamination, burn marks, and geometry defects. The model is trained on annotated examples of the defect types you care about, and holds up against the material, colour and surface variation that comes with recycled feedstock.
Do I need thousands of images to train the system?
No. Around 120 annotated images is enough to train a model. This is a large reduction compared to traditional systems that require thousands of manually labelled samples. It is however important to note that challenging applications typically perform better, the better the data.
Can Deepvis keep up with fast production speeds?
Yes — with the right GPU hardware, Deepvis can analyze parts in real time down to 0.5-second cycle times, making it suitable for high-speed packaging and manufacturinglines.
How is Deepvis different from traditional vision systems?
Traditional systems rely on rule-based image processing and require reprogramming every time a product changes. Deepvis uses AI to adapt to product variation and requires no specialist for setup, making it ideal for agile manufacturers where long and complex setuptimes are out of the question.
What's included in the Deepvis inspectionsystem?
Each unit includes a camera, AI edge computer, and software platform for inspection. Customers can purchase the full solution as a one-time investment, with optional software licensing and support packages.
How do I know if Deepvis is right for my application?
If your quality control process is manual, time-consuming, and affected by frequent changes in product, lighting, or material, Deepvis is built for you. Our system is designed to reduce man-hours in visual inspection — especially in high-volume, high-variation environments where traditional systems fall short. We typically start with a discovery call and a pilot to demonstrate time savings and operational impact.
Udforsk smartere kvalitetskontrol med Deepvis
Se hvordan AI-drevet visuel inspektion reducerer fejl, sænker omkostninger og tilpasser sig jeres produktionslinje — uden komplekst opsætningsarbejde.