| 176 | 3 | 13 |
| 下载次数 | 被引频次 | 阅读次数 |
针对现有X射线违禁品检测网络所需样本数量大、无法检测新类别的问题，提出了一种基于FPID的小样本X射线图像违禁品检测算法。该算法以MAML为基础，结合ECA-Net和多尺度特征融合，通过一维卷积生成通道注意力，学习通道之间的相关性，对深层特征和浅层特征充分融合，使模型有效提取不同任务之间的共性特征，利用微调策略实现违禁品检测。实验结果表明，该算法在提升检测准确率的同时计算量降低约70%,对未经训练的小样本违禁品检测效果达到81.72%。证明模型能够更快、更准确地识别出X射线图像中的违禁品。
Abstract：The existing X-ray prohibited item detection network requires a large number of samples and cannot detect new categories. To solve the above problem, an FPID-based small-sample X-ray image algorithm for prohibited item detection is proposed. The algorithm, based on MAML and combined with ECA-Net module and multi-scale feature fusion module, generates channel attention through one-dimensional convolution, learns the correlation between channels, and with a full fusion of deep features and shallow features, the model can effectively extract the common features of different tasks, and then use the fine-tuning strategy to achieve prohibited item detection. The experimental results show that the algorithm can improve the detection accuracy while reducing the calculation amount by about 70%, and the detection effect for untrained small-sample prohibited item reaches 81.72%. It is proved that the proposed model can identify prohibited items in X-ray images faster and more accurately.
[1] SZEGEDY C,LIU W,JIA Y,et al.Going Deeper with Convolutions [C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Boston:IEEE,2015:1-9.
[2] SIMONYAN K,ZISSERMAN A.Very Deep Convolutional Networks for Large-scale Image Recognition [J/OL].(2014-09-04) [2022-12-12] https://arxiv.org/abs/1409.1556.
[3] LIU J,LENG J,LIU Y.Deep Convolutional Neural Network Based Object Detector for X-ray Baggage Security Imagery [C]//2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI).Portland:IEEE,2019:1757-1761.
[4] MIAO C,XIE L,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,2019:2114-2123.
[5] 于重重，萨良兵，马先钦，等.基于度量学习的小样本零器件表面缺陷检测[J].仪器仪表学报，2020,41(7):214-223.
[6] 刘颖，雷研博，范九伦，等.基于小样本学习的图像分类技术综述[J].自动化学报，2021,47(2):297-315.
[7] WANG Y,YAO Q,KWOK J,et al.Generalizing from a Few Examples [J].ACM Computing Surveys (CSUR),2020,53(3):1-34.
[8] VINYALS O,BLUNDELL C,LILLICRAP T,et.al.Matching Networks for One Shot Learning [C]//NIPS′16:Proceedings of the 30th International Conference on Neural Information Processing Systems.Barcelona:Curran Associates Inc.,2016:3637-3645.
[9] LAROCHELLE S.Optimization as a Model for Few-shot Learning [C]//5th International Conference on Learning Representations (ICLR 2017).Toulon:[s.n.],2017:1-11.
[10] FINN C,ABBEEL P,LEVINE S.Model-agnostic Meta-learning for Fast Adaptation of Deep Networks [C]//ICML′17:Proceedings of the 34th International Conference on Machine Learning.Sydney:JMLR.org,2017:1126-1135.
[11] NICHOL A,ACHIAM J,SCHULMAN J.On First-order Meta-learning Algorithms [J/OL].(2018-03-08) [2022-12-12].https://arxiv.org/abs/1803.02999.
[12] WANG Q,WU B,ZHU P,et al.ECA-Net:Efficient Channel Attention for Deep Convolutional Neural Networks [C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle:IEEE,2020:11531-11539.
[13] WANG Y,YAO Q,KWOK J T,et al.Generalizing from a Few Examples:A Survey on Few-shot Learning [J].ACM Computing Surveys,2020,53(3):1-34.
[14] 谢江荣，李范鸣，卫红，等.用于空中红外目标检测的增强单发多框检测器方法[J].光学学报，2019,39(6):223-231.
[15] 金璐，刘士建，王霄，等.基于改进关系网络的小样本红外空中目标分类方法[J].光学学报，2020,40(8):87-96.
[16] 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 (CVPR).Las Vegas:IEEE,2016:2818-2826.
[17] HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas:IEEE,2015:770-778.
[18] SELVARAJU R R C M,DAS A,AL E.Grad-CAM:Visual Explanations from Deep Networks via Gradient-based Localization [C]//2017 IEEE International Conference on Computer Vision (ICCV).Venice:IEEE,2017:618-626.
基本信息:
DOI：
中图分类号:TP391.41;O434.19
引用信息:
[1]程振伟,李新伟.基于FPID的小样本X射线图像违禁品检测[J].无线电工程,2023,53(08):1836-1843.
基金信息:
河南省科技攻关计划项目(192102210099); 河南省高校基本科研业务费专项资金资助(NSFRF220444)~~