用图像质量评价量实现的真实图像和计算机生成图像的鉴别方法  

A New Approach to Distinguish Computer Generated Images from Real Images Using Image Quality Metrics

作　　者：张震[1,2] 康吉全[2] 平西建[1] 任远[2] 

机构地区：[1]信息工程大学信息工程学院,河南郑州450002 [2]郑州大学电气工程学院,河南郑州450001

出　　处：《测绘科学技术学报》2008年第5期355-358,共4页Journal of Geomatics Science and Technology

基　　金：国家自然科学基金(60473022)

摘　　要：真实图像和计算机生成图像的鉴别是数字图像盲取证中的一个重要问题。提出了一种真实图像和计算机生成图像的鉴别方法。借用模式识别中的二分类概念,采用图像质量评价量来建立模型,以捕获真实图像和计算机生成图像的统计差异,选用支持向量机作为分类器进行训练和测试。实验结果表明,该方法计算方便、实用性强、可靠性高。Discrimination between real images and computer generated images is an important issue in digital image forensics. This paper proposed a new detection scheme to discriminate computer generated images from real images. The detection could be regarded as a two-class pattern recognition problem, and the model was established using image quality metrics （IQM） extracted from the given test image. This model could capture statistical differences between real images and computer generated images. Kernel-based Support Vector Machine （SVM） was chosen as a classifier to train and test the given images. Experimental results demonstrated that this new detection scheme had some advantages of easy calculation, wide applications and high reliability.

关 键 词：真实图像 计算机生成图像 图像质量评价量 支持向量机 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] P237[自动化与计算机技术—计算机科学与技术]