ABSTRACT
Abstract: With the number of passengers increasing year by year, the pressure of security check in railway stations, airports and other transportation places is increasing. Long hours of high-intensity work can easily lead to fatigue of security inspectors, which makes it difficult for them to stay focused in front of the X-ray detection machine. This situation can easily lead to missed detection of controlled knives, and ultimately increase the safety risk of passengers during the journey. In order to solve the above problems, based on the YoloV5 model and the Convolutional Block Attention Module, this paper builds a detection model that can automatically identify the controlled knife in the X-ray image, which is used to help the security inspector to automatically detect the X-ray image in an efficient and fast way. The results show that the final mAP of X-ray image controlled knife detection model based on improved YoloV5 is 0.9169.
- Li Shanshan, Zhang Yi, Liu Wen, Yang Jiapeng, Hai Ling. An X-ray breast signs detection algorithm [J/OL]. Small microcomputer system: 1-8 [2022-10-30]. http://kns.cnki.net/kcms/detail/21.1106.TP.20221018.1339.036.html.Google Scholar
- Cao Yang, Zhang Li, Meng Junxi, Song Qian, Zhang Letian. Multi-target contraband recognition algorithm for X-ray security screening scenario [J]. Laser & Optoelectronics Progress, 222,59(10):324-332.Google Scholar
- Leyun Long, Luwu Zhou, Shuqin Liu, Biao Huang, Kai Fan. Research on Target Detection of transmission Line Breaking Risk based on Improved YOLOv5 Algorithm [J/OL]. Journal of electronic measurement and instrument: 1-10 [2022-10-30]. HTTP: / / http://kns.cnki.net/kcms/detail/11.2488.tn.20221026.1505.010.html.Google Scholar
- Li Ang, Sun Shijie, Zhang Chaoyang, Feng Mingtao, Wu Chengzhong, Li Wang. Lightweight Research of Improved YOLOv5s Track Obstacle Detection Model [J/OL]. Computer engineering and application: 1-15 [2022-10-30]. HTTP: / / http://kns.cnki.net/kcms/detail/11.2127.TP.20221026.1944.014.html.Google Scholar
- Chen Z. Research on movie recommendation algorithm based on CBAM-CNN model [D]. Anhui university of science and technology, 2021. DOI: 10.26918 /, dc nki. GHNGC. 2021.000649.Google Scholar
- Cui Junjun, Li Haiyang, Guo Shirui, Li Xiaolei, Cui Yinghao, Zheng Bo, Sun Manying. Laser Cladding Crack Identification based on Convolutional module attention mechanism deep learning model [J]. Laser and Optoelectronics Progress,2021,58(20):337-343.Google Scholar
- Yu Haibo, Chen Jinguang. Image description generation model based on convolution module block attention [J]. Computer system application, 2021, 30 (8) : 194-200. The DOI: 10.15888 / j.carol carroll nki. Csa. 008043.Google Scholar
Index Terms
- Controlled knife X-ray image detection model based on improved YoloV5
Recommendations
A marker-based watershed method for X-ray image segmentation
Digital X-ray images are the most frequent modality for both screening and diagnosis in hospitals. To facilitate subsequent analysis such as quantification and computer aided diagnosis (CAD), it is desirable to exclude image background. A marker-based ...
Vertebrae Segmentation from X-ray Images Using Convolutional Neural Network
IHIP 2018: Proceedings of the 2018 International Conference on Information Hiding and Image ProcessingNOTICE OF RETRACTION: While investigating potential publication-related misconduct in connection with the IHIP 2018 Conference Proceedings, serious concerns were raised that cast doubt on the integrity of the peer-review process and all papers published ...
3D/2D Image Registration: The Impact of X-Ray Views and Their Number
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2007AbstractAn important part of image-guided radiation therapy or surgery is registration of a three-dimensional (3D) preoperative image to two-dimensional (2D) images of the patient. It is expected that the accuracy and robustness of a 3D/2D image ...
Comments