噪声特征与EXIF信息相关性的图像篡改鉴定

doi:10.13190/j.jbupt.2014.01.002

北京邮电大学学报 ›› 2014, Vol. 37 ›› Issue (1): 6-10.doi: 10.13190/j.jbupt.2014.01.002

噪声特征与EXIF信息相关性的图像篡改鉴定

李叶舟¹, 孙晓婷¹, 牛少彰², 孟宪哲²

1. 北京邮电大学理学院, 北京 100876;
2. 北京邮电大学智能通信软件与多媒体北京市重点实验室, 北京 100876

收稿日期:2013-05-31 出版日期:2014-02-28 发布日期:2014-01-07
作者简介:李叶舟（1973—），女，副教授，E-mail：yezhouli@bupt.edu.cn.
基金资助:
国家自然科学基金项目（61070207，61370195）；北京市自然科学基金项目（4132060）；“十二五冶国家密码发展基金密码理论课题项目（MMJJ201201002）；国际自然科学基金青年基金项目（11101048）

Detecting Forgeriesby Correlation between Image Noise Features and EXIF Parameters

LI Ye-zhou¹, SUN Xiao-ting¹, NIU Shao-zhang², MENG Xian-zhe²

1. School of Science, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2013-05-31 Online:2014-02-28 Published:2014-01-07

摘要/Abstract

摘要：

建立了照片可交换图像文件（EXIF）信息中的5个常用参数与图像统计噪声之间的相关性，利用这种相关性对图像的真实性做出判断. 通过提取训练图像的统计噪声特征及5个EXIF特征，建立了二者的相关性，利用此相关性估计待检测图像的EXIF信息，再与照片本身的EXIF信息进行对比，进而判断其是否遭到篡改. 实验结果显示，利用提出的方法对图像是否经过照片滤镜和模糊等修改进行检测，得到了较好的检测结果.

关键词: 图像篡改, 交换图像文件参数, 噪声特征

Abstract:

In correlation between five common exchangeable image file (EXIF) parameters and image statistical noise for digital photos is built. The authenticity of the image is judged by this correlation. The statistical noise and five EXIF features from the training image are extracted, following the correlation established. Make use of the correlation to estimate EXIF information of testing images which will be compared with the real values. The comparison will determine the authenticity of testing images. Experiments on both tampered images and real images indicate the effectiveness of the proposed method.

Key words: image tampered, exchange image file parameters, noise features

中图分类号:

TN929.53

李叶舟, 孙晓婷, 牛少彰, 孟宪哲. 噪声特征与EXIF信息相关性的图像篡改鉴定[J]. 北京邮电大学学报, 2014, 37(1): 6-10.

LI Ye-zhou, SUN Xiao-ting, NIU Shao-zhang, MENG Xian-zhe. Detecting Forgeriesby Correlation between Image Noise Features and EXIF Parameters[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2014, 37(1): 6-10.

噪声特征与EXIF信息相关性的图像篡改鉴定

Detecting Forgeriesby Correlation between Image Noise Features and EXIF Parameters

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价