Sep 2026· 2026 11th International Conference on Computer Science and Engineering (UBMK)· pp. 420-422· 0 citations
TL;DR
The findings indicate that Transformer-based detectors require large-scale pre-training and substantially more data to be effective on small industrial defect datasets, and that Transformer-based detectors require large-scale pre-training and substantially more data to be effective on small industrial defect datasets.
Abstract
Autonomous detection of surface defects on Printed Circuit Boards (PCBs) in electronic production lines is crucial for efficiently improving quality control processes and enhancing PCB anomaly detection in line with Industry 4.0 standards. In this study, we compared the performance of a novel Transformer-based DETR architecture for PCB anomaly detection with the traditional CNN-based YOLOv8 architecture, the industry standard for object detection. We trained both models with the same dataset of industrial PCB defects and compared their detection accuracy, inference time, and sensitivity to structural defect data. Experimental results show that, on this small-scale industrial dataset, YOLOv8 converges quickly and reaches a high detection accuracy (93.8% mAP@0.50) with low inference time, whereas DETR fails to converge under the same data scale and training budget (0.00% mAP). These findings indicate that Transformer-based detectors require large-scale pre-training and substantially more data to be effective on small industrial defect datasets. This study demonstrates the advantages and disadvantages of different deep learning architectures in industrial integration tasks.
As the electronic manufacturing industry continues to evolve towards higher density and integration, the detection of micro-defects in printed circuit boards (PCBs) demands greater accuracy and efficiency. Traditional methods of manual visual inspection and machine vision lack generalization in complex backgrounds, whi...
Printed circuit board (PCB) defect detection is critical for ensuring the performance and reliability of electronic products. However, traditional inspection methods suffer from low efficiency and poor stability. In recent years, the development of deep learning models has proceeded at a rapid pace. But existing deep l...
With the advancement of electronic manufacturing towards high density and miniaturization, PCB soldering defect detection has become a critical component of industrial quality control. Traditional human visual inspection suffers from low efficiency, while existing deep learning algorithms generally face challenges such...
Hong-Quan Liu, Jian-Hui Jin, Jian-Ping Wang et al.· Engineering Research Express· 0 citations
This paper presents an all-encompassing system architecture for defect attributes, AI feature learning, defect detection and localisation, and performance evaluation and investigates how artificial intelligence can be used to address the problems of detecting small defects on PCBs.
Yu-Tian Gao· Applied and Computational En...· 0 citations
A lightweight real-time deep learning framework is proposed for industrial defect inspection, centering on an improved RT-DETR model that incorporates a large kernel attention backbone and a generalized layer aggregation network. This architecture addresses two issues: few-shot learning scenarios and stringent industri...
Jian-Rong Tian· International Conference on...· 0 citations
The proposed AI-Based PCB Fault Detection System uses computer vision and image processing techniques to analyze PCB images and identify potentially defective regions and displays detected results as a pass/fail status or a possible defect indication.
Yogini Diwate, Tejas Chamat, Bhavesh Mesharam et al.· International Journal for Re...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.