What question did this study set out to answer?

To resolve missed and false detections of tiny defects embedded within complex printed circuit board textures using an optimized neural network architecture.

June 16, 2023SHILAP Revista de lepidopterologíaOpen Access

Global contextual attention augmented YOLO with ConvMixer prediction heads for PCB surface defect detection

View Full Paper

Ask AI

Bookmark

To resolve missed and false detections of tiny defects embedded within complex printed circuit board textures using an optimized neural network architecture.
Constructed GCC-YOLO by integrating a high-resolution P2 layer, a global contextual attention module within the C3 backbone, and a bi-directional weighted feature pyramid network (BiFPN).
Incorporated a ConvMixer module into the prediction head to reduce network parameters while enhancing sensitivity to small defect targets.
Evaluated model precision, recall, and mean average precision against YOLOv5s and benchmark detection algorithms on a PCB defect dataset.
GCC-YOLO increased Precision by 0.2%, Recall by 1.8%, mAP@0.5 by 0.5%, and mAP@0.5:0.95 by 8.3% compared to YOLOv5s.
The architecture exhibited reduced model parameter volume and faster reasoning speed relative to comparator detection algorithms.

Authors

KXKewen XiaHebei University of Technology ZLZhongliang LvChongqing Technology and Business University KLKang LiuXidian University

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Algorithm evaluation demonstrates improved defect detection accuracy in printed circuit boards, highlighting the utility of lightweight attention-guided architectures.

Cite This Study

Xia et al. (2023) studied this question.

synapsesocial.com/papers/69da25b6b48bb130d468456c https://doi.org/10.1038/s41598-023-36854-2

View Full Paper

Ask AI

Bookmark

Implication

Algorithm evaluation demonstrates improved defect detection accuracy in printed circuit boards, highlighting the utility of lightweight attention-guided architectures.

Global contextual attention augmented YOLO with ConvMixer prediction heads for PCB surface defect detection

Key Points

Discussion

Implication

Cite This Study

Global contextual attention augmented YOLO with ConvMixer prediction heads for PCB surface defect detection

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider