【作者】 沈林杰； 孔祥维； 尤新刚；

【Author】 Shen Linjie1 Kong Xiangwei1 You Xingang1,2(1 Information Security Research Center,Dalian University of Technology, Dalian 116024, China)(2Beijing Institute of Electronic Technology and Application, Beijing 100091, China)

【机构】 大连理工大学信息安全研究中心；

【摘要】 为了认定打印文件的来源,提出一种基于字符图像质量评价的打印机取证方法.在分析字符打印区域“条带”噪声的基础上,通过高斯滤波对字符图像提取噪声,并借助图像质量评价方法提取噪声图像的统计特征,来描述每台打印机的个体特征,并采用支持向量机作为分类器.对比目前国外已有文献的方法,所提出的方法不仅10台打印机都判决正确,而且字符分类正确率有很大提高.字符图像质量特征抓住了打印机的个体特性,使取证结果有效且具有说服力.更多还原

【Abstract】 A new printer forensics method based on character image quality measures is put forward to identify the source of printed files. Based on the analysis of the properties of the “banding” noise in the character image extracted by Gaussian filter, the statistic features donating the characteristics of each printer are extracted using image quality measures (IQM), and support vector machine (SVM) is used as classifier to identify the source printers. Compared with other methods, the printers used in the experiment are all identified correctly and the accuracy of character identification is much higher with the proposed approach. The experimental results prove that the individual characteristics of each printer can be identified effectively by the character image quality measures.更多还原