Towards More Efficient Security Inspection via Deep Learning: A Task-Driven X-ray Image Cropping Scheme
X-ray imaging machines are widely used in border control checkpoints or public transportation, for luggage scanning and inspection. Recent advances in deep learning enabled automatic object detection of X-ray imaging results to largely reduce labor costs. Compared to tasks on natural images, object...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/13/4/565 |
| _version_ | 1797434346776297472 |
|---|---|
| author | Hong Duc Nguyen Rizhao Cai Heng Zhao Alex C. Kot Bihan Wen |
| author_facet | Hong Duc Nguyen Rizhao Cai Heng Zhao Alex C. Kot Bihan Wen |
| author_sort | Hong Duc Nguyen |
| collection | DOAJ |
| description | X-ray imaging machines are widely used in border control checkpoints or public transportation, for luggage scanning and inspection. Recent advances in deep learning enabled automatic object detection of X-ray imaging results to largely reduce labor costs. Compared to tasks on natural images, object detection for X-ray inspection are typically more challenging, due to the varied sizes and aspect ratios of X-ray images, random locations of the small target objects within the redundant background region, etc. In practice, we show that directly applying off-the-shelf deep learning-based detection algorithms for X-ray imagery can be highly time-consuming and ineffective. To this end, we propose a Task-Driven Cropping scheme, dubbed TDC, for improving the deep image detection algorithms towards efficient and effective luggage inspection via X-ray images. Instead of processing the whole X-ray images for object detection, we propose a two-stage strategy, which first adaptively crops X-ray images and only preserves the task-related regions, i.e., the luggage regions for security inspection. A task-specific deep feature extractor is used to rapidly identify the importance of each X-ray image pixel. Only the regions that are useful and related to the detection tasks are kept and passed to the follow-up deep detector. The varied-scale X-ray images are thus reduced to the same size and aspect ratio, which enables a more efficient deep detection pipeline. Besides, to benchmark the effectiveness of X-ray image detection algorithms, we propose a novel dataset for X-ray image detection, dubbed SIXray-D, based on the popular SIXray dataset. In SIXray-D, we provide the complete and more accurate annotations of both object classes and bounding boxes, which enables model training for supervised X-ray detection methods. Our results show that our proposed TDC algorithm can effectively boost popular detection algorithms, by achieving better detection mAPs or reducing the run time. |
| first_indexed | 2024-03-09T10:30:54Z |
| format | Article |
| id | doaj.art-29cf22bd80924ddb8f3e8222a27c3988 |
| institution | Directory Open Access Journal |
| issn | 2072-666X |
| language | English |
| last_indexed | 2024-03-09T10:30:54Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj.art-29cf22bd80924ddb8f3e8222a27c39882023-12-01T21:14:35ZengMDPI AGMicromachines2072-666X2022-03-0113456510.3390/mi13040565Towards More Efficient Security Inspection via Deep Learning: A Task-Driven X-ray Image Cropping SchemeHong Duc Nguyen0Rizhao Cai1Heng Zhao2Alex C. Kot3Bihan Wen4School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore 639798, SingaporeSchool of Electrical & Electronic Engineering, Nanyang Technological University, Singapore 639798, SingaporeSchool of Electrical & Electronic Engineering, Nanyang Technological University, Singapore 639798, SingaporeSchool of Electrical & Electronic Engineering, Nanyang Technological University, Singapore 639798, SingaporeSchool of Electrical & Electronic Engineering, Nanyang Technological University, Singapore 639798, SingaporeX-ray imaging machines are widely used in border control checkpoints or public transportation, for luggage scanning and inspection. Recent advances in deep learning enabled automatic object detection of X-ray imaging results to largely reduce labor costs. Compared to tasks on natural images, object detection for X-ray inspection are typically more challenging, due to the varied sizes and aspect ratios of X-ray images, random locations of the small target objects within the redundant background region, etc. In practice, we show that directly applying off-the-shelf deep learning-based detection algorithms for X-ray imagery can be highly time-consuming and ineffective. To this end, we propose a Task-Driven Cropping scheme, dubbed TDC, for improving the deep image detection algorithms towards efficient and effective luggage inspection via X-ray images. Instead of processing the whole X-ray images for object detection, we propose a two-stage strategy, which first adaptively crops X-ray images and only preserves the task-related regions, i.e., the luggage regions for security inspection. A task-specific deep feature extractor is used to rapidly identify the importance of each X-ray image pixel. Only the regions that are useful and related to the detection tasks are kept and passed to the follow-up deep detector. The varied-scale X-ray images are thus reduced to the same size and aspect ratio, which enables a more efficient deep detection pipeline. Besides, to benchmark the effectiveness of X-ray image detection algorithms, we propose a novel dataset for X-ray image detection, dubbed SIXray-D, based on the popular SIXray dataset. In SIXray-D, we provide the complete and more accurate annotations of both object classes and bounding boxes, which enables model training for supervised X-ray detection methods. Our results show that our proposed TDC algorithm can effectively boost popular detection algorithms, by achieving better detection mAPs or reducing the run time.https://www.mdpi.com/2072-666X/13/4/565X-ray imagingobjective detectionimage croppingdeep learningfeatures extraction |
| spellingShingle | Hong Duc Nguyen Rizhao Cai Heng Zhao Alex C. Kot Bihan Wen Towards More Efficient Security Inspection via Deep Learning: A Task-Driven X-ray Image Cropping Scheme Micromachines X-ray imaging objective detection image cropping deep learning features extraction |
| title | Towards More Efficient Security Inspection via Deep Learning: A Task-Driven X-ray Image Cropping Scheme |
| title_full | Towards More Efficient Security Inspection via Deep Learning: A Task-Driven X-ray Image Cropping Scheme |
| title_fullStr | Towards More Efficient Security Inspection via Deep Learning: A Task-Driven X-ray Image Cropping Scheme |
| title_full_unstemmed | Towards More Efficient Security Inspection via Deep Learning: A Task-Driven X-ray Image Cropping Scheme |
| title_short | Towards More Efficient Security Inspection via Deep Learning: A Task-Driven X-ray Image Cropping Scheme |
| title_sort | towards more efficient security inspection via deep learning a task driven x ray image cropping scheme |
| topic | X-ray imaging objective detection image cropping deep learning features extraction |
| url | https://www.mdpi.com/2072-666X/13/4/565 |
| work_keys_str_mv | AT hongducnguyen towardsmoreefficientsecurityinspectionviadeeplearningataskdrivenxrayimagecroppingscheme AT rizhaocai towardsmoreefficientsecurityinspectionviadeeplearningataskdrivenxrayimagecroppingscheme AT hengzhao towardsmoreefficientsecurityinspectionviadeeplearningataskdrivenxrayimagecroppingscheme AT alexckot towardsmoreefficientsecurityinspectionviadeeplearningataskdrivenxrayimagecroppingscheme AT bihanwen towardsmoreefficientsecurityinspectionviadeeplearningataskdrivenxrayimagecroppingscheme |