Deep learning for PCB X-ray image generation and restoration
This project explores the challenge of limited availability of X-ray PCB detection image datasets and proposes a solution using generation methods to generate X-ray style images as training datasets. The study compares the performance of supervised learning methods such as Generative Adversarial Net...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/166317 |
| _version_ | 1811684471309598720 |
|---|---|
| author | Wang, Xinrui |
| author2 | Wen Bihan |
| author_facet | Wen Bihan Wang, Xinrui |
| author_sort | Wang, Xinrui |
| collection | NTU |
| description | This project explores the challenge of limited availability of X-ray PCB detection image datasets and proposes a solution using generation methods to generate X-ray style images as training datasets. The study compares the performance of supervised learning methods such as Generative Adversarial Networks (GANs) and regressive methods such as U-net and Resnet in generating fake Xray images for PCB anomaly detection. The experiments showed that the U-net framework with L1 loss achieved the best results in generating high-quality fake
X-ray images. The study also suggests that using SSIM as the final evaluation metric can result in highly consistent evaluation with human judgement. The work provides a novel approach to X-ray data augmentation for PCB anomaly detection and offers insights into the use of regression training for synthesizing high-resolution images.
Keywords: X-ray image, PCB, Generation, GAN, U-Net. |
| first_indexed | 2024-10-01T04:29:09Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/166317 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:29:09Z |
| publishDate | 2023 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1663172023-07-04T15:11:04Z Deep learning for PCB X-ray image generation and restoration Wang, Xinrui Wen Bihan School of Electrical and Electronic Engineering bihan.wen@ntu.edu.sg Engineering::Electrical and electronic engineering This project explores the challenge of limited availability of X-ray PCB detection image datasets and proposes a solution using generation methods to generate X-ray style images as training datasets. The study compares the performance of supervised learning methods such as Generative Adversarial Networks (GANs) and regressive methods such as U-net and Resnet in generating fake Xray images for PCB anomaly detection. The experiments showed that the U-net framework with L1 loss achieved the best results in generating high-quality fake X-ray images. The study also suggests that using SSIM as the final evaluation metric can result in highly consistent evaluation with human judgement. The work provides a novel approach to X-ray data augmentation for PCB anomaly detection and offers insights into the use of regression training for synthesizing high-resolution images. Keywords: X-ray image, PCB, Generation, GAN, U-Net. Master of Science (Computer Control and Automation) 2023-04-24T02:26:35Z 2023-04-24T02:26:35Z 2023 Thesis-Master by Coursework Wang, X. (2023). Deep learning for PCB X-ray image generation and restoration. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/166317 https://hdl.handle.net/10356/166317 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering Wang, Xinrui Deep learning for PCB X-ray image generation and restoration |
| title | Deep learning for PCB X-ray image generation and restoration |
| title_full | Deep learning for PCB X-ray image generation and restoration |
| title_fullStr | Deep learning for PCB X-ray image generation and restoration |
| title_full_unstemmed | Deep learning for PCB X-ray image generation and restoration |
| title_short | Deep learning for PCB X-ray image generation and restoration |
| title_sort | deep learning for pcb x ray image generation and restoration |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/166317 |
| work_keys_str_mv | AT wangxinrui deeplearningforpcbxrayimagegenerationandrestoration |