Data Augmentation of Backscatter X-ray Images for Deep Learning-Based Automatic Cargo Inspection
Custom inspection using X-ray imaging is a very promising application of modern pattern recognition technology. However, the lack of data or renewal of tariff items makes the application of such technology difficult. In this paper, we present a data augmentation technique based on a new image-to-ima...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/21/7294 |
| _version_ | 1797511696084893696 |
|---|---|
| author | Hyunwoo Cho Haesol Park Ig-Jae Kim Junghyun Cho |
| author_facet | Hyunwoo Cho Haesol Park Ig-Jae Kim Junghyun Cho |
| author_sort | Hyunwoo Cho |
| collection | DOAJ |
| description | Custom inspection using X-ray imaging is a very promising application of modern pattern recognition technology. However, the lack of data or renewal of tariff items makes the application of such technology difficult. In this paper, we present a data augmentation technique based on a new image-to-image translation method to deal with these difficulties. Unlike the conventional methods that convert a semantic label image into a realistic image, the proposed method takes a texture map with a special modification as an additional input of a generative adversarial network to reproduce domain-specific characteristics, such as background clutter or sensor-specific noise patterns. The proposed method was validated by applying it to backscatter X-ray (BSX) vehicle data augmentation. The Fréchet inception distance (FID) of the result indicates the visual quality of the translated image was significantly improved from the baseline when the texture parameters were used. Additionally, in terms of data augmentation, the experimental results of classification, segmentation, and detection show that the use of the translated image data, along with the real data consistently, improved the performance of the trained models. Our findings show that detailed depiction of the texture in translated images is crucial for data augmentation. Considering the comparatively few studies that have examined custom inspections of container scale goods, such as cars, we believe that this study will facilitate research on the automation of container screening, and the security of aviation and ports. |
| first_indexed | 2024-03-10T05:51:45Z |
| format | Article |
| id | doaj.art-35adbe6a39f94563a90fff1916f4e633 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:51:45Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-35adbe6a39f94563a90fff1916f4e6332023-11-22T21:39:27ZengMDPI AGSensors1424-82202021-11-012121729410.3390/s21217294Data Augmentation of Backscatter X-ray Images for Deep Learning-Based Automatic Cargo InspectionHyunwoo Cho0Haesol Park1Ig-Jae Kim2Junghyun Cho3Center for Artificial Intelligence, Korea Institute of Science and Technology, Seoul 02792, KoreaCenter for Artificial Intelligence, Korea Institute of Science and Technology, Seoul 02792, KoreaCenter for Artificial Intelligence, Korea Institute of Science and Technology, Seoul 02792, KoreaCenter for Artificial Intelligence, Korea Institute of Science and Technology, Seoul 02792, KoreaCustom inspection using X-ray imaging is a very promising application of modern pattern recognition technology. However, the lack of data or renewal of tariff items makes the application of such technology difficult. In this paper, we present a data augmentation technique based on a new image-to-image translation method to deal with these difficulties. Unlike the conventional methods that convert a semantic label image into a realistic image, the proposed method takes a texture map with a special modification as an additional input of a generative adversarial network to reproduce domain-specific characteristics, such as background clutter or sensor-specific noise patterns. The proposed method was validated by applying it to backscatter X-ray (BSX) vehicle data augmentation. The Fréchet inception distance (FID) of the result indicates the visual quality of the translated image was significantly improved from the baseline when the texture parameters were used. Additionally, in terms of data augmentation, the experimental results of classification, segmentation, and detection show that the use of the translated image data, along with the real data consistently, improved the performance of the trained models. Our findings show that detailed depiction of the texture in translated images is crucial for data augmentation. Considering the comparatively few studies that have examined custom inspections of container scale goods, such as cars, we believe that this study will facilitate research on the automation of container screening, and the security of aviation and ports.https://www.mdpi.com/1424-8220/21/21/7294backscatter X-raydata augmentationcargo inspectiongenerative adversarial networkimage translation |
| spellingShingle | Hyunwoo Cho Haesol Park Ig-Jae Kim Junghyun Cho Data Augmentation of Backscatter X-ray Images for Deep Learning-Based Automatic Cargo Inspection Sensors backscatter X-ray data augmentation cargo inspection generative adversarial network image translation |
| title | Data Augmentation of Backscatter X-ray Images for Deep Learning-Based Automatic Cargo Inspection |
| title_full | Data Augmentation of Backscatter X-ray Images for Deep Learning-Based Automatic Cargo Inspection |
| title_fullStr | Data Augmentation of Backscatter X-ray Images for Deep Learning-Based Automatic Cargo Inspection |
| title_full_unstemmed | Data Augmentation of Backscatter X-ray Images for Deep Learning-Based Automatic Cargo Inspection |
| title_short | Data Augmentation of Backscatter X-ray Images for Deep Learning-Based Automatic Cargo Inspection |
| title_sort | data augmentation of backscatter x ray images for deep learning based automatic cargo inspection |
| topic | backscatter X-ray data augmentation cargo inspection generative adversarial network image translation |
| url | https://www.mdpi.com/1424-8220/21/21/7294 |
| work_keys_str_mv | AT hyunwoocho dataaugmentationofbackscatterxrayimagesfordeeplearningbasedautomaticcargoinspection AT haesolpark dataaugmentationofbackscatterxrayimagesfordeeplearningbasedautomaticcargoinspection AT igjaekim dataaugmentationofbackscatterxrayimagesfordeeplearningbasedautomaticcargoinspection AT junghyuncho dataaugmentationofbackscatterxrayimagesfordeeplearningbasedautomaticcargoinspection |