Holiday Cars · Inspektlabs
95% Reduction — Turnaround Time
Vendor-reportedTravel & hospitality · Quality inspection · Computer vision · In production
Quality inspection
Prohan · DAC.digital
Vendor-reportedManufacturingIn productionSmall businessComputer vision
Vendor-reported. The customer is named and the numbers are quoted from the source page, but the account comes from the vendor. No independent confirmation.
Reported by dac.digital (vendor self-report). Checked against the source page on 2026-09-06. 0 of 3 figures below appear on that page word for word; the rest are marked.
The problem
Errors in the production line of hardwood furniture led to significant financial losses and customer dissatisfaction due to undetected gaps, cracks, or splits in wood panels that were invisible to the human eye.
What was deployed
- Vendor
- DAC.digital
- Products
- computer vision-powered camera, custom Computer Vision System
- Technique
- Computer vision
- Build or buy
- Built in-house or to order
- Deployment
- Custom build
- Data used
- Photos of production processes classified as "definitiv kein Defekt", "definitiv Defekt" oder "Grenzfall".
- Scale
- continuously monitors the production line, operating 24/7
- Timeline
- 4 months
What changed
Each row is quoted from the source. Figures we could not find on the page in those words are marked — they are kept, not deleted, so you can judge them.
Defect detection rate
“Furthermore, defect detection throughout production increased by 90%.”
Not found on the source page in these words · round percentage, no baseline given
zeroCustomer returns due to defectssince the solution implementation
“Since the solution implementation, Prohan has not had a single return triggered by this type of flaw.”
Not found on the source page in these words
less than 0.5%Waste rate of glued panelsfrom 5%
“Before, for every 1000 glued panels, around 5% had to be discarded. Now this rate is less that 0,5%.”
Not found on the source page in these words
“Laut Prohan war die Lösung jedoch so gut konzipiert, dass keine Änderungen oder zusätzliche Algorithmus-Trainings erforderlich waren.”
Difficulties and limits
- Gaps, cracks, or splits in wood panels were often only a few tenths of a millimeter wide and passed through the machine at up to 30 meters per second, making them undetectable to the human eye.
- The production environment was dusty with poor lighting conditions.
- Off-the-shelf solutions could not meet the customer's specific requirements.
- Knot hole analysis was not implemented due to a low project ROI in relation to the customer's budget.
Sources
- dac.digital — vendor self-report, 2024-09-04
- dac.digital — vendor self-report, 2024-09-04
Similar deployments
MSM (MyMind Joint Stock Company) · CloudThinker
98.4% — Bug detection rate on AI-assisted pull requests
Vendor-reportedTechnology & software · Quality inspection · AI agents · Scaled
Root Insurance · Observe.AI
15% improvement — compliance
Vendor-reportedInsurance · Quality inspection · NLP · In production
Ancera · Voxel51
improved by over 7% — model performance
Vendor-reportedAgriculture · Quality inspection · Computer vision · In production
Mint Group Solutions · GuardSync AI
98% — Completion & Compliance Rate
Vendor-reportedOther · Quality inspection · Computer vision · In production
GE Aerospace
Independently reportedManufacturing · Process automation · Classical ML · Scaled