首页 | 本学科首页   官方微博 | 高级检索  
     

基于块效应网格偏移的重获取JPEG图像篡改检测
引用本文:黄维,黄添强,张雪莉,肖辉. 基于块效应网格偏移的重获取JPEG图像篡改检测[J]. 网络与信息安全学报, 2017, 3(12): 38-44. DOI: 10.11959/j.issn.2096-109x.2017.00220
作者姓名:黄维  黄添强  张雪莉  肖辉
作者单位:1. 福建师范大学数学与信息学院,福建 福州 350117;2. 福建省大数据挖掘与应用工程技术研究中心,福建 福州 350117
基金项目:国家自然科学基金资助项目(61070062);国家自然科学基金资助项目(61502103);福建省高校产学合作科技重大基金资助项目(2015H6007);福州市科技计划基金资助项目(2014-G-76);福建省高等学校新世纪优秀人才支持基金资助项目(JAI1038);福建省科学厅K类基金资助项目(2011007);福建省教育厅A类基金资助项目(JA10064)
摘    要:重获取图像是原始或篡改后的图像经过中间媒介的映射后再次拍摄获取的图像,一张高质量的重获取伪造图像很难通过人眼判别真伪。针对JPEG格式的重获取图像篡改操作,提出了一种重压缩块效应网格偏移的检测方法。重获取图像由于再获取过程会引入与原图不相关的背景信息,该图像进行多次压缩会产生块效应网格偏移,即重压缩产生的块效应网格会与原始的网格错匹配,利用图像的平均信息损失量进行块效应网格是否发生偏移来检测图像的原始性。实验表明,该方法比已有的重获取图像检测方法准确率更高,且平均检测时间更短。

关 键 词:图像取证  重获取图像  JPEG图像  重压缩  块效应网格偏移  

JPEG recapture image tamper detection method based on block effect grid offset
Wei HUANG,Tian-qiang HUANG,Xue-li ZHANG,Hui XIAO. JPEG recapture image tamper detection method based on block effect grid offset[J]. Chinese Journal of Network and Information Security, 2017, 3(12): 38-44. DOI: 10.11959/j.issn.2096-109x.2017.00220
Authors:Wei HUANG  Tian-qiang HUANG  Xue-li ZHANG  Hui XIAO
Affiliation:1. College of Mathematics and Informatics,Fujian Normal University,Fuzhou 350117,China;2. Fujian Provincial Engineering Research Center of Big Data Analysis and Application,Fuzhou 350117,China
Abstract:Recaptured images are captured original or distorted image shown on the intermediaries,a high-quality recapture image is difficult to distinguish the authenticity of the human eye.Aimed at the tampering operation of JPEG image,a method of detecting block effect grid offset due to re-compression was proposed.The original image was compressed multiple times did not produce the block effect of the grid offset,and the recapture image,because of the recapture process would introduce background information that was not related to the original image,the re-compression of the block effect grid with the original grid is mismatched,and the average information loss amount of the image was used to detect whether the block effect grid generates an offset or not to detect the recapture image.Experiments show that this method is more accurate than the existing recapture image detection method,and the average detection time is shorter.
Keywords:image forensics  recapture images  JPEG images  repetitive compression  offset of BAG  
点击此处可从《网络与信息安全学报》浏览原始摘要信息
点击此处可从《网络与信息安全学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号