Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 2 Current »

Infinite material inspection 

  • Textile inspection

  • Inspection of corks

  • Wood inspection - defects inspection, classification of knots

  • Leather inspection - scratches

Automotive

  • Lights Inspection

  • Brake Discs Inspection 

  • Interior - Plastic Parts Inspection 

PCB inspection 

  • Components Detection (identifying presence/absence, misplaced components)

  • Defects Classification (scratches,dent, welding defects, etc)

  • Tin Detection on PCB connectors

Glass manufacturing 

  • Inspection of baking bowls/forms - greatly increased quality

  • Inspection of glass bottles - classification and defects detection/classification

3D inspection (conversion of a 3D image to depth map)

  • Inspection of Eggs package

PEKAT VISION software is known for visual inspection using AI on 2D images. Lately, we tried to explore new possibilities and extend our inspection into a third dimension.

The case study was developed for an Eggs Package Inspection with Photoneo 3D scanner, then converting the original 3D images into depth maps, which are then loaded into PEKAT VISION software for accurate evaluation.

We used our Anomaly of Surface module to seek for any anomalies on the depth map, in this case cracked eggs. Because the broken part of the egg is lower than the normal surface, the difference is clearly visible in the depth map (the lowest parts have red color).

  • Inspection of Electric Vehicle (EV) batteries

In this scenario, depth map images were also obtained by 3D scanner, where defects were easily detected by our Anomaly of Surface module.

Others

  • Inspection of Coins (check for rust, scratches, dent, etc.)

  • 2D Inspection of batteries

  • 2D Defects Detection - Screws, Bolts, Nuts, Metallic/Plastic Parts, etc.

  • No labels

0 Comments

You are not logged in. Any changes you make will be marked as anonymous. You may want to Log In if you already have an account.