Abstract
In X-ray baggage inspection, due to the increase in the types of dangerous goods and the composition of the baggage contents, it is not suitable to clearly display various baggage and dangerous goods on the image acquired by the X-ray inspection system. In recent years, many deep learning-based object detection and recognition technologies have appeared, and object detection algorithms are also developing at a rapid pace along with the development of deep learning technologies. Object detection models commonly use convolution networks to process input values, but the convolution network has a problem of using a common filter regardless of the size of the object. This study aims to improve the accuracy of the threat objects detection algorithm in X-ray baggage images by applying deformable convolutional networks that make filters corresponding to objects using offsets. The proposed method was applied to Mask R-CNN(mask region based convolutional neural network) using GDXray and SIXray, which are X-ray security inspection image data sets, and the experimental results show that the proposed model performance can be improved compared to the existing algorithms.
REFERENCES
Zentai, G., X-ray imaging for homeland security, IEEE Int. Workshop Imag. Syst. Techniques (IST2008, (Chania, 2008). https://doi.org/10.1109/IST.2008.4659929
Akcay, S., Kundegorski, M.E., Devereux, M., and Breckon, T.P., Transfer learning using convolutional neural networks for object classification within X-ray baggage security imagery, IEEE Int. Conf. Image Process. (ICIP) (Phoenix, 2016), pp. 1057–1061. https://doi.org/10.1109/ICIP.2016.7532519
Schwaninger, A., Bolfing, A., Halbherr, T., Helman, S., Belyavin, A., and Hay, L., The impact of image based factors and training on threat detection performance in X-ray screening, Proc. Int. Conf. Res. Air Transp. (Fairfax, 2008), pp. 317–324. https://doi.org/10.13140/RG.2.1.1299.3526
Michel, S., Koller, S.M., de Ruiter, J.C., Moerland, R., Hogervorst, M., and Schwaninger, A., Computer-based training increases efficiency in X-ray image interpretation by aviation security screeners, Proc. 41st Annu. IEEE Int. Carnahan Conf. Secur. Technol. (Ottawa, 2007), pp. 201–206. https://doi.org/10.1109/CCST.2007.4373490
Turcsany, D., Mouton, A., and Breckon, T.P., Improving feature-based object recognition for X-ray baggage security screening using primed visual words, IEEE Int. Conf. Industr. Technol. (ICIT) (Capetown, 2013), pp. 1140–1145. https://doi.org/10.1109/ICIT.2013.6505833
Bastan, M., Yousefi, M.R., and Breuel, T.M., Visual words on baggage X-ray images, Comput. Anal. Imag. Patterns 14th Int. Conf. (CAIP 2011) (Seville, 2011), pp. 360–368. https://doi.org/10.1007/978-3-642-23672-3_44
Kundegorski, M.E., Akçay, S., Devereux, M., Mouton, A., and Breckon, T.P., On using feature descriptors as visual words for object detection within X-ray baggage security screening, Int. Conf. Imag. Crime Detection & Prevention (Madrid, 2016). https://doi.org/10.1049/ic.2016.0080
Bastan, M., Byeon, W., and Breuel, T.M., Object recognition in multi-view dual energy X-ray images, Proc. BMVC (Berlin, 2013), pp. 130–131. https://doi.org/10.1007/978-3-642-32717-9_15
Baştan, M., Multi-view object detection in dual-energy X-ray images, Mach. Vision Appl., 2015, vol. 26, no. 7, pp. 1045–1060. https://doi.org/10.1007/s00138-015-0706-x
Mery, D., Riffo, V., Zuccar, I., and Pieringer, C., Automated X-ray object recognition using an efficient search algorithm in multiple views, Conf. Comput. Vision Pattern Recognit. Workshops (Portland, 2013), pp. 368–374. https://doi.org/10.1109/CVPRW.2013.62
Mery, D., Svec, E., Arias, M., Riffo, V., Saavedra, J.M., and Banerjee, S., Modern computer vision techniques for X-ray testing in baggage inspection, IEEE Trans. Syst. Man Cyberne. Syst., 2017, vol. 47, no. 4, pp. 682–692. https://doi.org/10.1109/TSMC.2016.2628381
Akcay, S., Kundegorski, M.E., Willcocks, C.G., and Breckon, T.P., Using deep convolutional neural network architectures for object classification and detection within X-ray baggage security imagery, IEEE Trans. Inf. Forensics Secur., 2018, vol. 13, no. 9, pp. 2203–2215. https://doi.org/10.1109/TIFS.2018.2812196
Girshick, R., Donahue, J., Darrell, T., and Malik, J., Region-based convolutional networks for accurate object detection and segmentation, IEEE Trans. Pattern Anal. Mach. Intell., 2016, vol. 38, no. 1, pp. 142–158. https://doi.org/10.1109/TPAMI.2015.2437384
Ren, S., He, K., Girshick, R., and Sun, J., Faster R-CNN: Towards real-time object detection with region proposal networks, Proc. Adv. Neural Inf. Proces. Syst. (Montreal, 2015), pp. 91–99. https://doi.org/10.1109/TPAMI.2016.2577031
Dai, J., Li, Y., He, K., and Sun, J., R-FCN:Object detection via region-based fully convolutional networks, Proc. Adv. Neural Inf. Process. Syst. (2016), pp. 379–387. https://doi.org/10.48550/arXiv.1605.06409
Redmon, J. and Farhadi, A., YOLO9000: Better, faster, stronger, 2017 IEEE Conf. Comput. Vision Pattern Recognit. (CVPR) (Honolulu, 2017), pp. 7263–7271. https://doi.org/10.1109/CVPR.2017.690
He, K., Zhang, X., Ren, S., and Sun, J., Deep residual learning for image recognition, Conf. Comput. Vision Pattern Recognit. (Las Vegas, 2016). https://doi.org/10.1109/CVPR.2016.90
Krizhevskii, A., Sutskever, I., and Hinton, G.E., Imagenet classification with deep convolutional neural networks, Adv. Neural Inform. Proces. Syst. (2012), pp. 1097–1105. https://doi.org/10.1145/3065386
Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A.A., Inception-v4, inception-resnet and the impact of residual connections on learning, Proc. 31st AAAI Conf. Artif. Intell., (2017), pp. 4278–4284. https://doi.org/10.48550/arXiv.1602.07261
Kim, J. and Ri, J., Generative adversarial networks and faster-region convolutional neural networks based object detection in X-ray baggage security imagery, OSA Continuum, 2020, vol. 3, no. 12, pp. 3604–3614. https://doi.org/10.1364/OSAC.412523
Xu, M., Zhang, H., and Yang, J., Prohibited item detection in airport X- ray security images via attention mechanism based CNN, Chin. Conf. Pattern Recognit. & Comput. Vision (Guangzhou, 2018), pp. 429–439. https://doi.org/10.1007/978-3-030-03335-4_37
An, J., Zhang, H., Zhu, Y., and Yang, J., Semantic segmentation for prohibited items in baggage inspection, Proc. Int. Conf. Intell. Sci. Big Data Eng. (ISCIDE) (Nanjing, 2019), pp. 495–505. https://doi.org/10.1007/978-3-030-36189-1_41
Gu, B., Chen, G., and Luo, L., Automatic and robust object detection in x-ray baggage inspection using deep convolutional neural networks, IEEE Trans. Ind. Electron., 2021, vol. 68, no. 10, pp. 10248–10257. https://doi.org/10.1109/TIE.2020.3026285
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., and Wei, Y., Deformable convolutional networks, Proc. IEEE Int. Conf. Comput. Vision (2017), pp. 764–773. https://doi.org/10.1109/ICCV.2017.89
Wang, J., Chen, Y., Chakraborty, R., Yu, S.X., Orthogonal convolutional neural networks, Preprint, 2019. arXiv:1911.12207. https://doi.org/10.48550/arXiv.1911.12207
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A., You only look once: Unified, real-time object detection, Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) (Las Vegas, 2016), pp. J779–788. https://doi.org/10.1109/CVPR.2016.91
He, K., Gkioxari, G., Dollár, P., and Girshick, R., Mask r-cnn, Proc. IEEE Int. Conf. Comput. Vision (Venice, 2017), pp. 2961–2969. https://doi.org/10.1109/ICCV.2017.322
Ren, Y., Zhu, C., and Xiao, S., Deformable faster R-CNN with aggregating multi-layer features for partially occluded object detection in optical remote sensing images, Remote Sens., 2018, vol. 10, no. 9, pp. 1470–1470. https://doi.org/10.3390/rs10091470
Mery, D., Riffo, V., Zscherpel, U., Mondragón, G., Lillo, I., Zuccar, I., Lobel, H., and Carrasco, M., GDXray: The database of X-ray images for nondestructive testing, J. Nondestr. Eval., 2015, vol. 34, no. 4, p. 42. https://doi.org/10.1007/s10921-015-0315-7
Miao, C., Xie, L., Wan, F., Su, C., Liu, H., Jiao, J., and Ye, Q., SIXray: A large-scale security inspection X-ray benchmark for prohibited item discovery in overlapping images, IEEE Int. Conf. Comput. Vision Pattern Recognit. (CVPR) (Long Beach, 2019), pp. 2119–2128. https://doi.org/10.1109/CVPR.2019.00222
Taimur, H., Muhammad, S., Samet, A., Salman, K., Mohammed, B., Ernesto, D., and Naoufel, W., Meta-transfer learning driven tensor-shot detector for the autonomous localization and recognition of concealed baggage threats, Sensors, 2020, vol. 20, no. 22, p. 6450. https://doi.org/10.3390/s20226450
Hassan, T., Khan, S., Akcay, S., Bennamoun, M., and Werghi, N., Cascaded structure tensor framework for robust identification of heavily occluded baggage items from multi-vendor X-ray scans, IEEE Conf. Comput. Vision Pattern Recognit. (CVPR 2019) (Long Beach, 2019). https://doi.org/10.48550/arXiv.1912.04251
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., and Zisserman, A., The pascal visual object classes challenge, machine learning challenges, evaluating predictive uncertainty, visual object classification and recognizing textual entailment, MLCW 2005 (Southampton, 2005), pp. 117–176. https://doi.org/10.1007/11736790_8
Henderson, P. and Ferrari, V., End-to-end training of object class detectors for mean average precision, Asian Conf. Comput. Vision (Cham, 2016), pp. 198–213. https://doi.org/10.1007/978-3-319-54193-8_13
Tan, P.N., Steinbach, M., and Kumar, V., Introduction to Data Mining, London: Pearson, 2005.
Kingma, D.P. and Ba, J., Adam: A method for stochastic optimization, Proc. Int. Conf. Learn. Representations (ICLR) (2015). https://doi.org/10.48550/arXiv.1412.6980
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflicts of interest.
Rights and permissions
About this article
Cite this article
Kim, J., Ri, J. & Jo, H. Automatic Detection of Threat Objects in X-ray Baggage Inspection Using Mask Region-Based Convolutional Neural Network and Deformable Convolutional Network. Russ J Nondestruct Test 58, 1175–1184 (2022). https://doi.org/10.1134/S1061830922600733
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1061830922600733