| 基于图像噪声分析的计算机生成图像检测算法 |
| |
| 引用本文： | 陈香苹. 基于图像噪声分析的计算机生成图像检测算法[J]. 上海电力学院学报, 2010, 0(2) |
| |
| 作者姓名： | 陈香苹 |
| |
| 作者单位： | 上海交通大学电子工程系; |
| |
| 基金项目： | 国家“863”计划资助项目(2007AA01Z455); 国家自然科学基金资助项目(60772098,60772042); 教育部新世纪优秀人才支持计划资助项目(NCET-0600393); 2007年上海市曙光计划资助项目 |
| |
| 摘 要： | 计算机生成图像与自然图像在物理生成机理上的差异性导致其在噪声分布上具有明显的区别,据此提出一种基于图像噪声分析的计算机生成图像检测新方法。首先,用小波隐马尔可夫(MMT)模型对图像噪声进行预处理;接着,基于最大似然估计方法估测图像参考模式噪声;最后,在提取图像模式噪声统计距及其与参考模式噪声相关差值基础上,利用支持向量机(SVM)分类器进行鉴别。实验结果显示,较已有的典型算法,该算法具有更好的检测率。
|
| 关 键 词： | 计算机生成图像鉴别 模式噪声 小波域隐马尔科夫(MMT)模型 统计矩 相关差值系数 |
Identifying computer generated images based on analysis of image noise |
| |
| CHEN Xiang-ping. Identifying computer generated images based on analysis of image noise[J]. Journal of Shanghai University of Electric Power, 2010, 0(2) |
| |
| Authors: | CHEN Xiang-ping |
| |
| Affiliation: | Department.of Electronic Engineering,Shanghai Jiaotong University,Shanghai 200240,China |
| |
| Abstract: | The discrimination of computer generated images from real images becomes more and more important.A novel digital forensics technique to distinguish computer generated images from real images is proposed based on the differences in the noise distribution of images.More specifically,at first,image noise is preprocessed using wavelet-domain hidden Markov tree models,and then the pattern noise is estimated relying on maximum likelihood estimate,finally,feature vectors are extracted such as statistics and differ... |
| |
| Keywords: | computer generated image identification pattern noise wavelet-domain HMT statistics differential correlation coefficient |
|
| 点击此处可从《上海电力学院学报》浏览原始摘要信息 |
|
点击此处可从《上海电力学院学报》下载全文 |
|
