一种基于自适应阈值的图像伪造检测算法  

Adaptive Threshold-based Detection Algorithm for Image Copy-move Forgery

作　　者：康晓兵[1,2] 魏生民[2] 

机构地区：[1]西安理工大学印刷包装工程学院信息科学系,西安7100481 [2]西北工业大学现代设计与集成制造技术教育部重点实验室,西安710072

出　　处：《计算机科学》2011年第3期295-299,共5页Computer Science

基　　金：国家自然科学基金(50875215)资助

摘　　要：图像伪造检测是数字取证领域一个发展迅速的研究方向。复制-移动是最常见的图像伪造方式之一,其目的是通过隐藏或克隆对象来创建新的图像内容场景。复制-移动伪造检测的主要依据是图像中存在较大面积的相同或非常相似的区域对。针对以往检测方法对图像中存在同质纹理或均匀区域检测困难以及相关参数阈值选择不确定等现状,提出一种基于自适应阈值的图像复制-移动伪造检测算法,该算法不但使相关阈值的选择和估计更合理,而且能够自动识别和定位伪造区域。通过在包含同质或均匀区域的彩色伪造图像中的实验,进一步验证了本算法的有效性。Image forgery detection is a burgeoning research field in digital forensics.As a most common way of image tampering,copy-move forgery is used to conceal objects or clone regions to produce a non-existing image scene.The target of copy-move forgery detection is to identify bigger duplicated image regions which are same or extremely similar.We reviewed several methods proposed to achieve this goal.These methods failed in detecting digital images with homogeneous texture or uniform areas and selecting the appropriate thresholds.We presented a novel adaptive threshold-based detection algorithm for image copy-move forgery,which might be applied to the color images with homogeneous or smooth regions and identified and located forged image regions automatically if only reasonable thresholds were estimated.Experimental results on several forged images with various homogeneous or uniform regions were presented to demonstrate the effectiveness of the proposed algorithm.

关 键 词：数字图像取证 复制-移动伪造 被动式检测 自适应 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP309.2[自动化与计算机技术—计算机科学与技术]