计算机应用研究2017，Vol.34Issue(1)：314-316,3.DOI:10.3969/j.issn.1001-3695.2017.01.071
基于噪声方差估计的伪造图像盲检测方法
Blind image forgery detection method based on noise variance estimation
摘要
Abstract
This paper developed a new blind detection method on the synthesis of forgery digital images from different sources. Different digital image background noise variance was different.First of all,it decomposed the image by wavelet decomposition, and removed the high frequency interference of the corresponding region of the image from the HH sub band,improved the noise variance estimation algorithm.And then it divided the noise image into blocks and estimated the noise variance of each sub block.In the homogeneous region of texture,the fusion of the block with the closed variance was carried out to find out the region of the abnormal variance.The experimental results show that the proposed algorithm can improve the estimation accuracy of image noise variance,and locate the forgery image regions in homogeneous areas.关键词
伪造图像/图像噪声/边缘检测/噪声方差/小波变换Key words
image forgery/image noise/edge detect/noise variance/wavelet transform分类
信息技术与安全科学引用本文复制引用
李杭,郑江滨..基于噪声方差估计的伪造图像盲检测方法[J].计算机应用研究,2017,34(1):314-316,3.基金项目
陕西省科技统筹创新工程资助项目 （）
