Semi-supervised contour-driven broad learning system for autonomous segmentation of concealed prohibited baggage items
Abstract With the exponential rise in global air traffic, ensuring swift passenger processing while countering potential security threats has become a paramount concern for aviation security. Although X-ray baggage monitoring is now standard, manual screening has several limitations, including the p...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-12-01
|
| Series: | Visual Computing for Industry, Biomedicine, and Art |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42492-024-00182-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846101480549908480 |
|---|---|
| author | Divya Velayudhan Abdelfatah Ahmed Taimur Hassan Muhammad Owais Neha Gour Mohammed Bennamoun Ernesto Damiani Naoufel Werghi |
| author_facet | Divya Velayudhan Abdelfatah Ahmed Taimur Hassan Muhammad Owais Neha Gour Mohammed Bennamoun Ernesto Damiani Naoufel Werghi |
| author_sort | Divya Velayudhan |
| collection | DOAJ |
| description | Abstract With the exponential rise in global air traffic, ensuring swift passenger processing while countering potential security threats has become a paramount concern for aviation security. Although X-ray baggage monitoring is now standard, manual screening has several limitations, including the propensity for errors, and raises concerns about passenger privacy. To address these drawbacks, researchers have leveraged recent advances in deep learning to design threat-segmentation frameworks. However, these models require extensive training data and labour-intensive dense pixel-wise annotations and are finetuned separately for each dataset to account for inter-dataset discrepancies. Hence, this study proposes a semi-supervised contour-driven broad learning system (BLS) for X-ray baggage security threat instance segmentation referred to as C-BLX. The research methodology involved enhancing representation learning and achieving faster training capability to tackle severe occlusion and class imbalance using a single training routine with limited baggage scans. The proposed framework was trained with minimal supervision using resource-efficient image-level labels to localize illegal items in multi-vendor baggage scans. More specifically, the framework generated candidate region segments from the input X-ray scans based on local intensity transition cues, effectively identifying concealed prohibited items without entire baggage scans. The multi-convolutional BLS exploits the rich complementary features extracted from these region segments to predict object categories, including threat and benign classes. The contours corresponding to the region segments predicted as threats were then utilized to yield the segmentation results. The proposed C-BLX system was thoroughly evaluated on three highly imbalanced public datasets and surpassed other competitive approaches in baggage-threat segmentation, yielding 90.04%, 78.92%, and 59.44% in terms of mIoU on GDXray, SIXray, and Compass-XP, respectively. Furthermore, the limitations of the proposed system in extracting precise region segments in intricate noisy settings and potential strategies for overcoming them through post-processing techniques were explored (source code will be available at https://github.com/Divs1159/CNN_BLS .) |
| format | Article |
| id | doaj-art-5eb907c3b93b42dfa1c60ec4527c7e43 |
| institution | Kabale University |
| issn | 2524-4442 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Visual Computing for Industry, Biomedicine, and Art |
| spelling | doaj-art-5eb907c3b93b42dfa1c60ec4527c7e432024-12-29T12:09:12ZengSpringerOpenVisual Computing for Industry, Biomedicine, and Art2524-44422024-12-017111810.1186/s42492-024-00182-7Semi-supervised contour-driven broad learning system for autonomous segmentation of concealed prohibited baggage itemsDivya Velayudhan0Abdelfatah Ahmed1Taimur Hassan2Muhammad Owais3Neha Gour4Mohammed Bennamoun5Ernesto Damiani6Naoufel Werghi7Department of Electrical Engineering and Computer Sciences, Center for Cyber-Physical Systems, Khalifa University of Science and TechnologyDepartment of Electrical Engineering and Computer Sciences, Center for Cyber-Physical Systems, Khalifa University of Science and TechnologyDepartment of Electrical, Computer and Biomedical Engineering, Abu Dhabi UniversityDepartment of Electrical Engineering and Computer Sciences, Center for Cyber-Physical Systems, Khalifa University of Science and TechnologyDepartment of Electrical Engineering and Computer Sciences, Center for Cyber-Physical Systems, Khalifa University of Science and TechnologyDepartment of Computer Science and Software Engineering, the University of Western AustraliaDepartment of Electrical Engineering and Computer Sciences, Center for Cyber-Physical Systems, Khalifa University of Science and TechnologyDepartment of Electrical Engineering and Computer Sciences, Center for Cyber-Physical Systems, Khalifa University of Science and TechnologyAbstract With the exponential rise in global air traffic, ensuring swift passenger processing while countering potential security threats has become a paramount concern for aviation security. Although X-ray baggage monitoring is now standard, manual screening has several limitations, including the propensity for errors, and raises concerns about passenger privacy. To address these drawbacks, researchers have leveraged recent advances in deep learning to design threat-segmentation frameworks. However, these models require extensive training data and labour-intensive dense pixel-wise annotations and are finetuned separately for each dataset to account for inter-dataset discrepancies. Hence, this study proposes a semi-supervised contour-driven broad learning system (BLS) for X-ray baggage security threat instance segmentation referred to as C-BLX. The research methodology involved enhancing representation learning and achieving faster training capability to tackle severe occlusion and class imbalance using a single training routine with limited baggage scans. The proposed framework was trained with minimal supervision using resource-efficient image-level labels to localize illegal items in multi-vendor baggage scans. More specifically, the framework generated candidate region segments from the input X-ray scans based on local intensity transition cues, effectively identifying concealed prohibited items without entire baggage scans. The multi-convolutional BLS exploits the rich complementary features extracted from these region segments to predict object categories, including threat and benign classes. The contours corresponding to the region segments predicted as threats were then utilized to yield the segmentation results. The proposed C-BLX system was thoroughly evaluated on three highly imbalanced public datasets and surpassed other competitive approaches in baggage-threat segmentation, yielding 90.04%, 78.92%, and 59.44% in terms of mIoU on GDXray, SIXray, and Compass-XP, respectively. Furthermore, the limitations of the proposed system in extracting precise region segments in intricate noisy settings and potential strategies for overcoming them through post-processing techniques were explored (source code will be available at https://github.com/Divs1159/CNN_BLS .)https://doi.org/10.1186/s42492-024-00182-7Baggage X-ray imageryBroad learning systemsThreat detectionThreat segmentation |
| spellingShingle | Divya Velayudhan Abdelfatah Ahmed Taimur Hassan Muhammad Owais Neha Gour Mohammed Bennamoun Ernesto Damiani Naoufel Werghi Semi-supervised contour-driven broad learning system for autonomous segmentation of concealed prohibited baggage items Visual Computing for Industry, Biomedicine, and Art Baggage X-ray imagery Broad learning systems Threat detection Threat segmentation |
| title | Semi-supervised contour-driven broad learning system for autonomous segmentation of concealed prohibited baggage items |
| title_full | Semi-supervised contour-driven broad learning system for autonomous segmentation of concealed prohibited baggage items |
| title_fullStr | Semi-supervised contour-driven broad learning system for autonomous segmentation of concealed prohibited baggage items |
| title_full_unstemmed | Semi-supervised contour-driven broad learning system for autonomous segmentation of concealed prohibited baggage items |
| title_short | Semi-supervised contour-driven broad learning system for autonomous segmentation of concealed prohibited baggage items |
| title_sort | semi supervised contour driven broad learning system for autonomous segmentation of concealed prohibited baggage items |
| topic | Baggage X-ray imagery Broad learning systems Threat detection Threat segmentation |
| url | https://doi.org/10.1186/s42492-024-00182-7 |
| work_keys_str_mv | AT divyavelayudhan semisupervisedcontourdrivenbroadlearningsystemforautonomoussegmentationofconcealedprohibitedbaggageitems AT abdelfatahahmed semisupervisedcontourdrivenbroadlearningsystemforautonomoussegmentationofconcealedprohibitedbaggageitems AT taimurhassan semisupervisedcontourdrivenbroadlearningsystemforautonomoussegmentationofconcealedprohibitedbaggageitems AT muhammadowais semisupervisedcontourdrivenbroadlearningsystemforautonomoussegmentationofconcealedprohibitedbaggageitems AT nehagour semisupervisedcontourdrivenbroadlearningsystemforautonomoussegmentationofconcealedprohibitedbaggageitems AT mohammedbennamoun semisupervisedcontourdrivenbroadlearningsystemforautonomoussegmentationofconcealedprohibitedbaggageitems AT ernestodamiani semisupervisedcontourdrivenbroadlearningsystemforautonomoussegmentationofconcealedprohibitedbaggageitems AT naoufelwerghi semisupervisedcontourdrivenbroadlearningsystemforautonomoussegmentationofconcealedprohibitedbaggageitems |