ESRPCB: an Edge guided Super - Resolution model and Ensemble learning for tiny Printed Circuit Board Defect detection

Thanh Nguyen Canh

Dang Bui Dinh

Van-Truong Nguyen

School of Information Science, JAIST, Japan
VNU University of Engineering and Technology, Vietnam
EAAI, 2025.

[Paper]

[Code]

Printed Circuit Boards (PCBs) are critical components in modern electronics, which require stringent quality control to ensure proper functionality. However, the detection of defects in small-scale PCBs images poses significant challenges as a result of the low resolution of the captured images, leading to potential confusion between defects and noise. To overcome these challenges, this paper proposes a novel framework, named ESRPCB (edgeguided super-resolution for PCBs defect detection), which combines edgeguided super-resolution with ensemble learning to enhance PCBs defect detection. Our approach leverages the edge information to guide the EDSR (Enhanced Deep Super-Resolution) model with a novel ResCat (Residual Concatenation) structure, enabling it to reconstruct high-resolution images from small PCBs inputs. By incorporating edge features, the super-resolution process preserves critical structural details, ensuring that tiny defects remain distinguishable in the enhanced image. Following this, a multi-modal defect detection model employs ensemble learning to analyze the super-resolved image, improving the accuracy of defect identification. Experimental results demonstrate that ESRPCB achieves superior performance compared to State-of-the-Art (SOTA) methods. Our model attains an average Peak Signal to Noise Ratio (PSNR) of 30.54 dB(decibel), surpassing EDSR by 0.42dB. In defect detection, ESRPCB achieves a mAP50(mean average precision at an Intersection over Union threshold of 0.50) of 0.965, surpassing EDSR (0.905) and traditional super-resolution models by over 5%. Furthermore, our ensemble-based detection approach further enhances performance, achieving a mAP50 of 0.977. These results highlight the effectiveness of ESRPCB in enhancing both image quality and defect detection accuracy, particularly in challenging low-resolution scenarios.

Paper

Xiem HoangVan, Thanh Nguyen Canh, Dang Bui Dinh, Van-Truong Nguyen Chong

ESRPCB: an Edge guided Super - Resolution model and Ensemble learning for tiny Printed Circuit Board Defect detection

EAAI 2025.

[pdf]

Overview

The architecture of the proposed ESRPCB Network.


The comparison of residual blocks in original ResNet (He et al. (2016)), SRResNet (Ledig et al. (2017)), EDSR (Lim et al. (2017)) and our ResCat.

Experiments Results

Trade-off between accuracy metrics (mAP50) and model parameters on the PCB Defect dataset with various SR models and the multimodal detection model. Our method is highlighted in red.

isual comparison of super-resolution results for various models on ×4 scale. The ground truth and reconstructed images are compared across metrics (PSNR/SSIM). Red highlights the best performance, and blue indicates the second-best.

Defect detection results comparison.

Quantitative Comparison of Average PSNR and SSIM for Super-Resolution Models.

Comparison of Residual Blocks Across Different Models.

Computational complexity comparison of Super-Resolution Models.

Comparison of mAP50 scores for Super-Resolution Models, red highlights the best performance, and bold values represent the ground truth (GT).

Code

[github]

Citation

1. HoangVan X., Canh T. N., Dinh B. D., Nguyen V-T. ESRPCB: an Edge guided Super - Resolution model and Ensemble learning for tiny Printed Circuit Board Defect detection. Symposium on System Integration (EAAI), 2025.

@article{hoangvan2025esrpcb, 
                                  

                                    author    = {HoangVan, Xiem and Canh, Thanh Nguyen and Dang, Bui Dinh and Nguyen, Van-Truong}, 
                                  

                                    title     = {{ESRPCB: an Edge guided Super - Resolution model and Ensemble learning for tiny Printed Circuit Board Defect detection}}, 
                                  

                                    booktitle = {Engineering Applications of Artificial Intelligence (EAAI)}, 
                                  

                                    year      = {2025}, 
                                  

                                    address   = {}, 
                                  

                                    month     = {}, 
                                  

                                    DOI       = {}
                                  

                                }

Acknowledgements

This research is funded by Vietnam National Foundation for Science and Technology Development (NAFOSTED) under grant number NCUD.022024.09.
This webpage template was borrowed from https://akanazawa.github.io/cmr/.