Xinrui Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xinrui Wang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Deruo Cheng
Nanyang Technological University
3 shared publications - Yiqiong Shi
Nanyang Technological University
3 shared publications - Bah-Hwee Gwee
Nanyang Technological University
2 shared publications - Feng Ji
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
2 shared publications - Bihan Wen
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore
1 shared publication - Hong Duc Nguyen
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore
1 shared publication
Latest Publications
- Open Access
- 3 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Data Descriptions
- Vol. 3, 237-244
Meta: Graph-Encoded Printed Circuit Board Datasets for Component Classification With Graph Neural Networks
We present a graph-based framework for Printed Circuit Board (PCB) image analysis, targeting core hardware assurance (HA) tasks such as IC segmentation and component identification. PCB images differ fundamentally from natural images in texture simplicity, spatial sparsity, and lack of informative backgrounds, limiting the effectiveness of traditional vision models. We propose GraphPCB, a generic scheme that transforms PCB images into graph-structured data, where nodes represent localized component regions and edges encode spatial proximity. This representation enables the application of Graph Neural Networks (GNNs) to PCB understanding, offering robustness to geometric variations and background noise. We release two high-quality GraphPCB datasets and analyze their structural properties, including graph heterophily and domain-specific challenges. Extensive experiments with various GNN architectures provide benchmarks and insights, establishing GraphPCB as a new testbed for node classification in structured visual domains.
- 3 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Data Descriptions
- Vol. 3, 237-244
Open AccessMeta: Graph-Encoded Printed Circuit Board Datasets for Component Classification With Graph Neural Networks
We present a graph-based framework for Printed Circuit Board (PCB) image analysis, targeting core hardware assurance (HA) tasks such as IC segmentation and component identification. PCB images differ fundamentally from natural images in texture simplicity, spatial sparsity, and lack of informative backgrounds, limiting the effectiveness of traditional vision models. We propose GraphPCB, a generic scheme that transforms PCB images into graph-structured data, where nodes represent localized component regions and edges encode spatial proximity. This representation enables the application of Graph Neural Networks (GNNs) to PCB understanding, offering robustness to geometric variations and background noise. We release two high-quality GraphPCB datasets and analyze their structural properties, including graph heterophily and domain-specific challenges. Extensive experiments with various GNN architectures provide benchmarks and insights, establishing GraphPCB as a new testbed for node classification in structured visual domains.
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
Data-Efficient Deep Learning for Printed Circuit Board Defect Detection Using X-Ray Images
Automated Optical Inspection (AOI) is widely used by manufacturers for the detection of defects in Printed Circuit boards (PCBs). Recent works have proposed to apply deep learning for defect detection, which is much faster and cheaper than manual inspection. However, AOI can only capture defects on the outmost layers of PCBs using cameras, while modern high-speed circuit PCBs usually have multiple internal layers that need to be inspected. Compared to optical sensors, X-ray tomography provides non-invasive imaging results of all PCB layers. Though one can directly apply an off-the-shelf deep detection model trained on optical domains for X-ray imagery, we show that it usually leads to much lower accuracies in practice. The degraded performance is mainly due to the relatively low quality of X-ray imaging results and the gaps between optical and X-ray modalities. Furthermore, no X-ray PCB image dataset is publicly available for training deep defect detectors. To this end, we propose a novel dataset for X-ray PCB defect detection, dubbed XD-PCB. In XD-PCB, we provide a benchmark for training X-ray automated defect detection models containing synthesized X-ray images and real X-ray images with real defects. However, in a practical environment, retraining the deep model for every unseen X-ray domain is inefficient due to the domain gaps created by different X-ray machine settings and the scarcity of defects. Thus, we propose a domain adaptation framework, dubbed FDX, to improve the efficiency of X-ray PCB defect detection methods. By minimizing the differences between the deep features extracted from abundant training images and the scarce unseen images, we improve the model’s performance in a practical situation, thus enhancing the generalization ability and efficiency of deep detection algorithms when exposed to unseen domains. Our results demonstrate that XD-PCB provides a valuable training baseline for X-ray PCB defect detection, and our proposed FDX framework can effectively increase the popular deep learning model by achieving an increment of 10% in terms of APs compared to other adaptation methods.
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
Data-Efficient Deep Learning for Printed Circuit Board Defect Detection Using X-Ray Images
Automated Optical Inspection (AOI) is widely used by manufacturers for the detection of defects in Printed Circuit boards (PCBs). Recent works have proposed to apply deep learning for defect detection, which is much faster and cheaper than manual inspection. However, AOI can only capture defects on the outmost layers of PCBs using cameras, while modern high-speed circuit PCBs usually have multiple internal layers that need to be inspected. Compared to optical sensors, X-ray tomography provides non-invasive imaging results of all PCB layers. Though one can directly apply an off-the-shelf deep detection model trained on optical domains for X-ray imagery, we show that it usually leads to much lower accuracies in practice. The degraded performance is mainly due to the relatively low quality of X-ray imaging results and the gaps between optical and X-ray modalities. Furthermore, no X-ray PCB image dataset is publicly available for training deep defect detectors. To this end, we propose a novel dataset for X-ray PCB defect detection, dubbed XD-PCB. In XD-PCB, we provide a benchmark for training X-ray automated defect detection models containing synthesized X-ray images and real X-ray images with real defects. However, in a practical environment, retraining the deep model for every unseen X-ray domain is inefficient due to the domain gaps created by different X-ray machine settings and the scarcity of defects. Thus, we propose a domain adaptation framework, dubbed FDX, to improve the efficiency of X-ray PCB defect detection methods. By minimizing the differences between the deep features extracted from abundant training images and the scarce unseen images, we improve the model’s performance in a practical situation, thus enhancing the generalization ability and efficiency of deep detection algorithms when exposed to unseen domains. Our results demonstrate that XD-PCB provides a valuable training baseline for X-ray PCB defect detection, and our proposed FDX framework can effectively increase the popular deep learning model by achieving an increment of 10% in terms of APs compared to other adaptation methods.