End-to-end deep learning framework for printed circuit board manufacturing defect classification

Abhiroop Bhattacharya, Sylvain G. Cloutier

Scientific Reports 2022 article cited by 133

importance 6/10 solved Industrial Vision Systems and Defect Detection electronics manufacturing stage: research

Quickly and accurately detecting and classifying the types of manufacturing defects present on printed circuit boards.

Automated, accurate PCB defect detection supports manufacturing quality control at scale.

A complete deep-learning framework using a single-step object detection model detects and classifies PCB defects, benchmarked against FRCNN-ResNet50, RetinaNet and YOLO on the same PCB defect dataset.

98.1% mAP (IoU=0.5) on low-resolution test images; 3.2% above low-resolution SOTA (YOLOv5m) and 1.4% above high-resolution SOTA (FRCNN-ResNet FPN); ~3x fewer parameters (7.02M).

Outperformed state-of-the-art baselines on the same dataset with roughly 3x fewer parameters.

Venue Scientific Reports
Published 2022
Work type article
Authors Abhiroop Bhattacharya, Sylvain G. Cloutier
Citations 133 (OpenAlex, at import time)
References 69
Model or method single-step object detection model (specific name not stated in source)
Organization not stated in source
Primary source https://doi.org/10.1038/s41598-022-16302-3
Open access gold
Keywords deep learning, PCB defect detection, object detection, YOLO, benchmark
6 / 10

significant — thousands to millions affected

Abstract states quality control is the major bottleneck of the PCB manufacturing chain and automation could raise yield/throughput and cut costs; no quantified scale.

Basis: stated. The source itself states the scale. Stated scale: not stated in source. Method and limits.

# Paper Year Citations Importance
1 Scaling deep learning for materials discovery
Amil Merchant, Simon Batzner, Samuel S. Schoenholz, Muratahan Aykol, G...
2023 1,471
8
2 Application of Machine Learning in Material Synthesis and Property Prediction
Guannan Huang, Yani Guo, Ye Chen, Zhengwei Nie
2023 165
7
3 Machine learning-guided discovery of ionic polymer electrolytes for lithium metal batteries
Kai Li, Jifeng Wang, Yuanyuan Song, Ying Wang
2023 115
7
4 Machine Learning for Structural Health Monitoring of Aerospace Structures: A Review
Gennaro Scarselli, Francesco Nicassio
2025 44
7
5 Power System Transient Stability Assessment Based on Machine Learning Algorithms and Grid Topology
Mihail D. Senyuk, Murodbek Safaraliev, Firuz Kamalov, Hana Sulieman
2023 42
7