SolVisionCase Study

Construction| Petrochemicals

AI Visual Inspection of Drywall Panels

Detecting subtle defects in complex backgrounds 

Drywall panels in building construction

Shaped like boards, drywall is commonly material in construction known for its fire and earthquake resistance, heat and sound insulation properties. It is used for building ceilings and walls, and in recent years have been offered in different embossed patterns and prints that break away from stereotypical impressions.

Complex embossed patterns and craftsmanship

Before a drywall leaves the production line, it is checked for cleanliness and pattern consistency. Stains, dirt, excessive or unclear printing need to be detected. However, the unique characteristics and appearance of embossed patterns create fuzzy looking defects on complex backgrounds that manual and conventional inspection systems have trouble identifying. 

AI enabled advanced visual inspection

Powered by AI, SolVision can automate visual inspections through high level image processing, recognizing defective products regardless of defect type or severity. The AI model can be trained to accurately detect and locate the defects on the drywall to improve product quality and production yield. 

AI Inspection

Incorrect Embossing and Scratches

Defect detection case of embossed gypsum board

Dirt

Defect detection case of embossed gypsum board

Overlarge Embossing Pattern

Defect detection case of embossed gypsum board
Related Posts
  • male professional checking the condition of a fire extinguisher

    Fire Extinguisher Inspection Using AR + AI

    Discover how a company improved fire extinguisher inspections by implementing META-aivi, enabling real-time issue detection, streamlining processes, and reducing inspection time by 60%.
  • A Man Fixing a Laptop

    Detecting Faulty and Missing Laptop Components

    For repetitive manual tasks such as in this case, an automated visual inspection can help identify defective products and improve workforce efficiency.

  • Inspecting Ball Grid Array Soldering Defects with AI

    Powered by deep learning, SolVision AI recognizes ball grid array soldering defects in overlapped solder balls through labeling of sample images.

  • AI Visual Inspection on Ribbons

    Using Solomon SolVision’s Instance Segmentation tool, all kinds of colored and patterned ribbons can be inspected to locate different defects big or small.