Capsule Attention Based Detection of Contraband in X-Ray Images
Downloads
Aiming at the problem of low detection accuracy caused by the different postures, different sizes, complex backgrounds and overlapping occlusions of contraband in the security checking process, a Matrix capsule network based on attention mechanism (MCAM) is designed by introducing attention mechanism into the capsule network. Firstly, a multi-feature-extraction (MFE) module is designed to solve the difficulty of detecting contraband with different sizes and complex backgrounds; then the Conv2d with Attention for ConvCap (CACC) is constructed in the convolutional layer of the capsule, and the weight information is computed in the channel dimensions of the feature map to give the contraband regions higher coefficients to enhance the contraband detection ability when the poses are different and the occlusion is severe; finally, a new capsule detection layer is designed by utilizing the pose matrix of the capsule to give full play to the detection ability of the matrix capsule network. The mAPs of the proposed model on SIXray, SIXray10, and SIXray100 are 85.10%, 64.05%, and 53.67%, respectively, which are 42.79%, 19.73%, and 9.41% higher than those of the original network, higher than those of the current mainstream detection networks, and the number of parameters of the network and the amount of computation are also lower.
W Y Q, R J J, YU Q. Impact Analysis of X-ray Machine Conveyor Belt Speed on Airport Security Missing Rate[J].China Transportation Review, 2017,39(05):55-59. (in Chinese).
YANG X G, YANG L R.. A Method on X-ray Security Image Enhancement[J]. CT Theory and Applications, 2012, 21(4): 705-712.(in Chinese)
Sterchi Y , Hattenschwiler N , Michel S ,et al.[IEEE 2017 International Carnahan Conference on Security Technology (ICCST) - Madrid (2017.10.23-2017.10.26)] 2017 International Carnahan Conference on Security Technology (ICCST) - Relevance of visual inspection strategy and knowledge about everyday objects for X-ray baggage screening[J]. 2017:1-6.DOI:10.1109/ccst.2017.8167812..
YAN W，JING H. Object detection in X-ray images based on object candidate extraction and support vector machine［C］// Ninth International Conference on Natural Computation. May 19，2014，Shenyang，China. IEEE，2014：173-177.
Heitz G , Chechik G .Object separation in X-ray image sets[J].IEEE, 2010.DOI:10.1109/CVPR.2010.5539887.
Xiao Y , Wang S , Wang Z ,et al.Coordinated-security based on probabilistic shaping and encryption in MMW-RoF system.[J].Optics letters, 2023, 48 11:, 2989-2992. DOI:10.1364/ol.493644.
Mery D .Automated detection in complex objects using a tracking algorithm in multiple X-ray views[C]//Computer Vision & Pattern Recognition Workshops.IEEE, 2011.DOI:10.1109/CVPRW.2011.5981715.
Hassan T , Akcay S , Bennamoun M ,et al.Trainable Structure Tensors for Autonomous Baggage Threat Detection Under Extreme Occlusion[C]//2020.DOI:10.1007/978-3-030-69544-6_16.
Akcay S , Kundegorski M E , Willcocks C G ,et al.Using Deep Convolutional Neural Network Architectures for Object Classification and Detection Within X-Ray Baggage Security Imagery[J].IEEE Transactions on Information Forensics and Security, 2018:2203-2215.DOI:10.1109/TIFS.2018.2812196.
CHENG L,JING Ch,CHEN W P. Algorithm for contraband detectedn in X-ray images based on neural network architecture search[J]. Science Technology and Engineering,2024,24(02):665-675.(in Chinese).
WANG H Q,WEI P X. X-ray image contraband detection based on improved YOLOv8[J/OL]. Radio Engineering,1-9[2024-02-27].(in Chinese).
ZHANG L,XUE ZH CH. X-ray contraband detection based on adaptive multiscale feature fusion[J/OL]. Signal Processing,1-18[2024-02-27].(in Chinese).
YUAN J H, ZHANG N F, RUAN J SH, GAO X D. Detection of prohibited items in X-ray images based on modified YOLOX algorithm[J]. LASER TECHNOLOGY, 2023, 47(4): 547-552.(in Chinese).
YOU X, HOU J, REN D SH, YANG P X, DU M SH. Adaptive Security Check Prohibited Items Detection Method with Fused Spatial Attention[J]. Computer Engineering and Applications, 2023, 59(21): 176-186.(in Chinese).
DONG Y SH, LI ZH X,GUO J Y . Improved YOLOv5 Model for X-Ray Prohibited Item Detection[J]. Laser & Optoelectronics Progress, 2023, 60(4): 0415005.(in Chinese).
Miao C , Xie L , Wan F ,et al.SIXray: A Large-Scale Security Inspection X-Ray Benchmark for Prohibited Item Discovery in Overlapping Images[J].IEEE, 2019.DOI:10.1109/CVPR.2019.00222.
He K , Zhang X , Ren S ,et al.Deep Residual Learning for Image Recognition[J].IEEE, 2016.DOI:10.1109/CVPR.2016.90.
M SH, LI X W, YANG Y et al. X-ray image contraband detection based on improved capsule network[J]. Journal of Henan University of Science and Technology(Natural Science Edition),2023,42(03):129-136.DOI:10.16186/j.cnki.1673-9787.2021080065.(in Chinese).
Hinton G E , Sabour S , Frosst N .Matrix capsules with EM routing[C]//2018.
Wang T , Zhang S .DSC-Ghost-Conv: A compact convolution module for building efficient neural network architectures[J].Multimedia Tools and Applications, 2023.DOI:10.1007/s11042-023-16120-3.
SZEGEDY C，VANHOUCKE V，IOFFE S，et al. Rethinking the inception architecture for computer vision［C］// 2016 IEEE Conference on Computer Vision and Pattern Recognition，Jun. 27-30，2016，Las Vegas，NV，USA.IEEE，2016：2818-2826.
Howard A , Sandler M , Chu G ,et al. Searching for MobileNetV3[J]. 2019.DOI:10.48550/arXiv.1905.02244.
Tan M , Le Q V .EfficientNetV2: Smaller Models and Faster Training[J]. 2021.DOI:10.48550/arXiv.2104.00298.
SELVARAJU R R，COGSWELL M，DAS A，et al. Grad-CAM：Visual explanations from deep net works via gradient-based localization［C］// International Conference on Computer Vision，Oct.22-29，2017，Venice，Italy. IEEE，2017：618-626.
