BIOENGINEER

Attention-enhanced YOLOv8s advances photovoltaic defect detection

An attention-enhanced version of the YOLOv8s computer-vision model achieved a precision of 93.2%, an F1-score of 92.7% and a ...
BIOENGINEER

Lightweight EDGI-YOLO improves steel surface defect detection in image-based benchmark study

A benchmark study found that EDGI-YOLO improved mAP@0.5 by 3.94 percentage points over YOLOv8n on NEU-DET while reducing ...

Physical AI in manufacturing: How computer vision, robotics and edge automation are moving into the real world

Physical AI is taking artificial intelligence beyond software and into factories, hospitals and other real-world environments. Computer vision, spatial systems, robotics and edge computing are ...
Semiconductor Engineering

Refining Vision-Language Models For Lithography Defect Detection

“Semiconductor lithography inspection requires reliable detection of small pattern defects such as bridge, burr, pinch, and contamination. In this study, we propose a two-stage vision-language ...
Woodworking Network

Muskoka Cabinet test drives real-time edgebanding defect detection system

The system, developed by Panevo, a Canadian clear technology and manufacturing analytics company, reportedly achieved approximately 97% detection reliability with minimal false positives of Muskoka’s ...