基于孪生网络的数字图像相机源识别

方梦华; 林果园

Chinese

您当前的位置：

首页 >

文章列表页 >

基于孪生网络的数字图像相机源识别

更新时间：2026-09-04

- 基于孪生网络的数字图像相机源识别
- Source identification of digital image based on Siamese network
- 微电子学与计算机 2021年38卷第6期页码：82-86
- 作者机构：
  
  1. 中国矿业大学计算机科学与技术学院,江苏,徐州,221116
  2. 矿山数字化教育部工程研究中心机构,江苏,徐州,221116
- 作者简介：
- 基金信息：
  
  软件新技术国家重点实验室开放基金项目 KFKT2018B27中央高校基础研究基金项目 2017XKQY079
- DOI：
  中图分类号：
- 纸质出版：2021
- 稿件说明：
移动端阅览
方梦华, 林果园. 基于孪生网络的数字图像相机源识别[J]. 微电子学与计算机, 2021, 38(6): 82-86, 92.

FANG Meng-hua, LIN Guo-yuan. Source identification of digital image based on Siamese network[J]. 2021, 38(6): 82-86.
方梦华, 林果园. 基于孪生网络的数字图像相机源识别[J]. 微电子学与计算机, 2021, 38(6): 82-86, 92. DOI：

FANG Meng-hua, LIN Guo-yuan. Source identification of digital image based on Siamese network[J]. 2021, 38(6): 82-86. DOI：

摘要

传统的利用传感器模式噪声的相机源识别方法，自动化程度低.直接使用深度学习方法进行识别，提取特征阶段又更倾向于学习到图像内容有关的特征，而不是相机“指纹”特征.为了解决上述问题，本文设计了一种基于孪生网络的数字图像相机源识别架构，两个网络分支共享权重.采用加入注意力机制的深度残差网络进行特征提取，抑制图像内容等因素对整个相机源识别任务的影响.对比实验结果表明，本文提出的方法在一定程度上提高了相机源识别的准确率.

Abstract

The traditional camera source identification method using sensor pattern noise has a low degree of automation. The deep learning method is directly used for identification

and the feature extraction stage is more inclined to learn the features related to the image content

rather than the camera "fingerprint" feature. In order to solve the above problems

this paper designs a digital image camera source identification architecture based on the Siamese network

and the two network branches share the weight. A deep residual network with an attention mechanism is used for feature extraction to suppress the influence of image content on the entire camera source identification task. The comparative experiment results show that the method proposed in this paper improves the accuracy of camera source identification to a certain extent.

关键词

Keywords

references

蒋翔, 韦世奎, 赵瑞珍, 等. 数字图像的设备溯源技术综述[J]. 北京交通大学学报, 2019, 43(2): 48-57. DOI: 10.11860/j.issn.1673-0291.20190036. JIANG X, WEI S K, ZHAO R Z, et al. Survey of imaging device source identification[J]. Journal of Beijing Jiaotong University, 2019, 43(2): 48-57. DOI: 10.11860/j.issn.1673-0291.20190036.

FERREIRA A, CHEN H, LI B, et al. An inception-based data-driven ensemble approach to camera model identification[C]//Proceedings of 2018 IEEE International Workshop on Information Forensics and Security. Hong Kong, China: IEEE, 2018: 1-7. DOI: 10.1109/WIFS.2018.8630774.

AHMED F, KHELIFI F, LAWGALY A, etal. Comparative analysis of a deep convolutional neural network for source camera identification[C]//Proceedings of the 2019 IEEE 12th International Conference on Global Security, Safety and Sustainability. London: IEEE, 2019: 1-6. DOI: 10.1109/ICGS3.2019.8688260.

蒋英春. 基于成像传感器特征的相机源识别[J]. 计算机工程与应用, 2012, 48(18): 193-196. DOI: 10.3778/j.issn.1002-8331.2012.18.041. JIANG Y C. Source camera identification based on characteristics of imaging sensor[J]. Computer Engineering and Applications, 2012, 48(18): 193-196. DOI: 10.3778/j.issn.1002-8331.2012.18.041.

GLOE T, BÖHME R. The 'Dresden Image Database' for benchmarking digital image forensics[C]//Proceedings of the 2010 ACM Symposium on Applied Computing. Sierre, Switzerland: ACM, 2010: 1584-1590. DOI: 10.1145/1774088.1774427.

MAYER O, STAMM M C. Learned forensic source similarity for unknown camera models[C]//Proceedings of 2018 IEEE International Conference on Acoustics, Speech and Signal Processing. Calgary, Canada: IEEE, 2018: 2012-2016. DOI: 10.1109/ICASSP.2018.8462585.

CHEN M, FRIDRICH J, GOLJAN M, et al. Determining image origin and integrity using sensor noise[J]. IEEE Transactions on Information Forensics and Security, 2008, 3(1): 74-90. DOI: 10.1109/TIFS.2007.916285.

陈凌翔, 柯永振, 孙玉婷. 一种用于图片来源检测的相机参考模式噪声提取算法[J]. 计算机工程, 2017, 43(12): 227-230. DOI: 10.3969/j.issn.1000-3428.2017.12.041. CHEN L X, KE Y Z, SUN Y T. A camera reference pattern noise extraction algorithm for image source detection[J]. Computer Engineering, 2017, 43(12): 227-230. DOI: 10.3969/j.issn.1000-3428.2017.12.041.

ZHAO M N, WANG B, WEI F, et al. Source camera identification based on coupling coding and adaptive filter[J]. IEEEAccess, 2020, 8: 54431-54440. DOI: 10.1109/ACCESS.2019.2959627.

AN Y, WANG B, ZHAO M J, et al. Patch-based sensor pattern noise for camera source identification[C]//Proceedings of 2015 IEEE China Summit and International Conference on Signal and Information Processing. Chengdu: IEEE, 2015: 866-870. DOI: 10.1109/ChinaSIP.2015.7230528.

LUKASJ, FRIDRICH J, GOLJAN M. Digital camera identification from sensor pattern noise[J]. IEEE Transactions on Information Forensics and Security, 2006, 1(2): 205-214. DOI: 10.1109/TIFS.2006.873602.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向处理器分支预测单元的Spectre攻击轻量化防御方法

大模型发展综述：从BERT到Deepseek的技术演进

基于反向体偏置的高增益稳定性高温运放设计

一种基于特征上下文理解与切片分析的肺结核检测算法

基于多尺度融合与小目标增强的航拍车辆检测算法