Open AccessX-ray security check image recognition based on attention mechanism
Author(s) -
Xiru Wu,
Chao Liu
Publication year - 2022
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2216/1/012104
Subject(s) - computer science , image (mathematics) , process (computing) , artificial intelligence , data mining , pattern recognition (psychology) , computer vision , operating system
In order to improve the detection efficiency and accuracy of the security check process, a detection algorithm that can accurately detect dangerous goods is constructed based on the attention mechanism and combined with the DETR algorithm. Combining the X-ray image data samples collected by the actual security inspection, the image data is trained through the deep learning network and analyzed on the verification data. The results show that the algorithm has higher verification accuracy, and the accuracy is higher than that of traditional detection algorithms, and it can locate dangerous goods more accurately. The method given in this article provides theoretical support and reference for the actual security inspection process.