非抽样Contourlet变换去噪滤波器设计的源相机识别  

Source camera identification based on nonsubsampled Contourlet transform denoising filter design

作　　者：陈宗民[1] 周治平[1] 

机构地区：[1]江南大学物联网工程学院,江苏无锡214122

出　　处：《计算机应用》2012年第2期507-509,513,共4页journal of Computer Applications

摘　　要：针对源相机识别和小波滤波器在获取残留噪声图像时会引入明显的场景噪声的问题,提出一种利用非抽样Contourlet变换(NSCT)进行模式噪声提取的新方案。首先根据源相机识别的过程,讨论小波滤波器在提取模式噪声上的不足,接着重点讨论设计基于NSCT滤波器进行模式噪声的提取。实验表明NSCT滤波器不仅使场景噪声得到明显的抑制,而且与小波滤波器相比,对来自三种不同相机的照片的平均识别率提高了近3.667%。Because obvious noise will occur when source camera identification and wavelet filters are getting the residual noise in the image scene, a new method for the extraction of pattern noise was proposed based on Nonsubsampled Contourlet Transform （ NSCT）. According to the process of source camera identification, the deficiencies of wavelet-based filter for the extraction of pattern noise were discussed first. And then, the discussion focused on the design of NSCT-based filter to extract pattern noise. The experimental results show that NSCT-based filter not only restrains the scene noise obviously, but also improves the average identification rate with 3.7% for identifying images from three different cameras compared to waveletbased filter.

关 键 词：数字图像取证 源相机识别 模式噪声 非抽样CONTOURLET变换 NEYMAN-PEARSON准则 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]