当前位置>主页 > 期刊在线 > 计算机技术 >

计算机技术21年3期

基于深度学习的安检图像检测及应用
王伊琳
(西北政法大学 信息网络中心,陕西 西安 710122)

摘  要:传统的人工安全检查的方式效率不高,针对这一问题提出一种基于掩码区域卷积神经网络的 X 光安检图像检测算法。首先选取 1 300 幅安检图像,对其中的训练样本以液体为目标进行标记,然后通过不同的网络提取图像特征并获得包含目标的建议区域,再输入到分类、回归、掩码三个分支网络进行训练,最终得到权重优化的 X 光安检图像检测模型。实验结果表明,基于深度学习的算法能够有效地对安检图像进行自动检测,且能够获得较高的准确率。


关键词:卷积神经网络;深度学习;X 光安检图像;检测识别



DOI:10.19850/j.cnki.2096-4706.2021.03.022


中图分类号:TP391.4                                 文献标识码:A                                     文章编号:2096-4706(2021)03-0082-04


Security Image Detection and Application Based on Deep Learning

WANG Yilin

(Information Network Center,Northwest University of Political Science and Law,Xi’an 710122,China)

Abstract:The traditional manual security inspection method is inefficient. In order to solve this problem,a detection algorithm of security X-ray images is proposed based on mask regional convolution neural network. First,1 300 security images are selected, and the training samples are labeled with liquid as the target. Then,the image features are extracted through different networks and the recommended region containing the target is obtained. Then,it is input into three branch networks of classification,regression and mask for training. Finally,the weight optimized X-ray image detection model is obtained. The experimental results show that the algorithm based on deep learning can effectively detect the security image automatically,and can obtain high accuracy.

Keywords:convolutional neural network;deep learning;security X-ray image;detection and recognition


参考文献:

[1] 刘颖,王伊琳,王倩,等 . 基于有偏彩色纹理字典的 X 光 安检图像检测 [J]. 西安邮电大学学报,2017,22(6):35-39.

[2] 张春兰 . 安检系统中 X 射线透射图像处理方法研究 [D]. 沈阳:沈阳大学,2015.

[3] 韩宁 . 基于深度学习的 X 射线图像危险品检测与跟踪算法 研究 [D]. 兰州:兰州大学,2018.

[4] HE K M,GKIOXARI G,DOLLÁR P,et al. Mask R-CNN [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020,42(1):386-397.

[5] REN S Q,HE K M,GIRSHICK R,et al. Faster-RCNN: Towards Real-Time Object Detection with Region Proposal Networks [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39(6):1137-1149.

[6] LIN T Y,DOLLÁR P,GIRSHICK R,et al. Feature Pyramid Networks for Object Detection [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Honolulu:IEEE,2017: 936-944.

[7] 王森,杨克俭 . 基于双线性插值的图像缩放算法的研究与 实现 [J]. 自动化技术与应用,2008(7):44-45+35.

[8] 冯冬青 . 基于深度学习的船只光学遥感图像检测和分割 [D]. 四川:电子科技大学,2019.

[9] MIAO C J,XIE L X,WAN F,et al. SIXray:A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Long Beach:IEEE,2019:983-993.


作者简介:王伊琳(1993—),女,汉族,陕西西安人,助理 工程师,硕士研究生,研究方向:视频与图像处理、高校信息化。