A Framework for the Synthesis of X-Ray Security Inspection Images Based on Generative Adversarial Networks
Object detection of prohibited items in X-ray security inspection is challenging because of serious overlap, disorderly background, and high throughput. In the past few years, a variety of deep learning algorithms have been proposed and achieved satisfactory results. However, the performance of thes...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10158706/ |
| _version_ | 1797792158084759552 |
|---|---|
| author | Jian Liu Tim H. Lin |
| author_facet | Jian Liu Tim H. Lin |
| author_sort | Jian Liu |
| collection | DOAJ |
| description | Object detection of prohibited items in X-ray security inspection is challenging because of serious overlap, disorderly background, and high throughput. In the past few years, a variety of deep learning algorithms have been proposed and achieved satisfactory results. However, the performance of these algorithms relies heavily on the specified datasets. Moreover, establishing a large-scale X-ray image dataset by manually collecting and labeling images is prohibitively expensive and time consuming. In this paper, we propose a text-driven framework for synthesizing X-ray security inspection images based on Generative Adversarial Networks (GAN). First, a conditional GAN is developed to generate natural images of prohibited items from class labels. Second, an improved model based on a pix-to-pix GAN is implemented to convert natural images into X-ray images. Third, another HD pix-to-pixel GAN is responsible for producing high-resolution benign background images, which are subsequently fused with the generated images of prohibited items to create X-ray inspection images. Finally, the proposed method is evaluated using SOTA object detection algorithms, such as YOLO-v5, and achieving 4.6% promotion for <inline-formula> <tex-math notation="LaTeX">$mAP_{0.5}$ </tex-math></inline-formula> and 15.9% promotion for <inline-formula> <tex-math notation="LaTeX">$mAP_{0.5-0.95}$ </tex-math></inline-formula>. The experimental results demonstrate that our image synthesis framework can effectively augment the datasets of prohibited items and improve the detection performance of deep learning algorithms during X-ray security screening. |
| first_indexed | 2024-03-13T02:29:11Z |
| format | Article |
| id | doaj.art-6853d157c6ad419bb3077aa53095956b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T02:29:11Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6853d157c6ad419bb3077aa53095956b2023-06-29T23:00:41ZengIEEEIEEE Access2169-35362023-01-0111637516376010.1109/ACCESS.2023.328808710158706A Framework for the Synthesis of X-Ray Security Inspection Images Based on Generative Adversarial NetworksJian Liu0https://orcid.org/0000-0003-2981-2128Tim H. Lin1School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, Henan, ChinaDepartment of Electrical and Computer Engineering, California State Polytechnic University, Pomona, CA, USAObject detection of prohibited items in X-ray security inspection is challenging because of serious overlap, disorderly background, and high throughput. In the past few years, a variety of deep learning algorithms have been proposed and achieved satisfactory results. However, the performance of these algorithms relies heavily on the specified datasets. Moreover, establishing a large-scale X-ray image dataset by manually collecting and labeling images is prohibitively expensive and time consuming. In this paper, we propose a text-driven framework for synthesizing X-ray security inspection images based on Generative Adversarial Networks (GAN). First, a conditional GAN is developed to generate natural images of prohibited items from class labels. Second, an improved model based on a pix-to-pix GAN is implemented to convert natural images into X-ray images. Third, another HD pix-to-pixel GAN is responsible for producing high-resolution benign background images, which are subsequently fused with the generated images of prohibited items to create X-ray inspection images. Finally, the proposed method is evaluated using SOTA object detection algorithms, such as YOLO-v5, and achieving 4.6% promotion for <inline-formula> <tex-math notation="LaTeX">$mAP_{0.5}$ </tex-math></inline-formula> and 15.9% promotion for <inline-formula> <tex-math notation="LaTeX">$mAP_{0.5-0.95}$ </tex-math></inline-formula>. The experimental results demonstrate that our image synthesis framework can effectively augment the datasets of prohibited items and improve the detection performance of deep learning algorithms during X-ray security screening.https://ieeexplore.ieee.org/document/10158706/Image generationdata augmentationobject detectionX-ray security checkinggenerative adversarial network (GAN) |
| spellingShingle | Jian Liu Tim H. Lin A Framework for the Synthesis of X-Ray Security Inspection Images Based on Generative Adversarial Networks IEEE Access Image generation data augmentation object detection X-ray security checking generative adversarial network (GAN) |
| title | A Framework for the Synthesis of X-Ray Security Inspection Images Based on Generative Adversarial Networks |
| title_full | A Framework for the Synthesis of X-Ray Security Inspection Images Based on Generative Adversarial Networks |
| title_fullStr | A Framework for the Synthesis of X-Ray Security Inspection Images Based on Generative Adversarial Networks |
| title_full_unstemmed | A Framework for the Synthesis of X-Ray Security Inspection Images Based on Generative Adversarial Networks |
| title_short | A Framework for the Synthesis of X-Ray Security Inspection Images Based on Generative Adversarial Networks |
| title_sort | framework for the synthesis of x ray security inspection images based on generative adversarial networks |
| topic | Image generation data augmentation object detection X-ray security checking generative adversarial network (GAN) |
| url | https://ieeexplore.ieee.org/document/10158706/ |
| work_keys_str_mv | AT jianliu aframeworkforthesynthesisofxraysecurityinspectionimagesbasedongenerativeadversarialnetworks AT timhlin aframeworkforthesynthesisofxraysecurityinspectionimagesbasedongenerativeadversarialnetworks AT jianliu frameworkforthesynthesisofxraysecurityinspectionimagesbasedongenerativeadversarialnetworks AT timhlin frameworkforthesynthesisofxraysecurityinspectionimagesbasedongenerativeadversarialnetworks |