| 图像内容感知缩放的检测方法研究 |
| |
| 引用本文： | 胡浩慧,倪蓉蓉,赵耀.图像内容感知缩放的检测方法研究[J].软件学报,2018,29(4):1002-1016. |
| |
| 作者姓名： | 胡浩慧 倪蓉蓉 赵耀 |
| |
| 作者单位： | 北京交通大学信息科学研究所, 北京 100044;现代信息科学与网络技术北京市重点实验室, 北京 100044,北京交通大学信息科学研究所, 北京 100044;现代信息科学与网络技术北京市重点实验室, 北京 100044,北京交通大学信息科学研究所, 北京 100044;现代信息科学与网络技术北京市重点实验室, 北京 100044 |
| |
| 基金项目： | 国家自然科学基金（61672090，61332012）；“多媒体内容取证方法研究”（61332012）；“视觉媒体篡改的取证和关联分析关键技术研究（61672090）；国家重点研发计划（2016YFB0800404）；中央高校基本科研业务费专项基金（2015JBZ002） |
| |
| 摘 要： | 针对可用于图像篡改的内容感知缩放技术，本文提出了一种基于概率Map图统计特征的内容感知缩放检测算法.该算法利用概率Map图来反映图像是否经过内容感知缩放操作，并利用新提出的积分投影与局部统计特征来检测篡改图像.而后利用分类器进行分类训练，从而有效识别基于内容感知缩放操作的图像篡改.实验结果显示，所提算法能够区分出原始图像与篡改图像，并具有较高的正确检测率.
|
| 关 键 词： | 内容感知缩放 统计特性 概率图 图像篡改 |
| 收稿时间： | 2017/4/30 0:00:00 |
| 修稿时间： | 2017/6/26 0:00:00 |
Research on Detection Method of Content-Aware Image Resizing |
| |
| HU Hao-Hui,NI Rong-Rong and ZHAO Yao.Research on Detection Method of Content-Aware Image Resizing[J].Journal of Software,2018,29(4):1002-1016. |
| |
| Authors: | HU Hao-Hui NI Rong-Rong and ZHAO Yao |
| |
| Affiliation: | Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China;Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing 100044, China,Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China;Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing 100044, China and Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China;Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing 100044, China |
| |
| Abstract: | In order to deal with the forged image using content-aware resizing, the content-aware resizing detection algorithm based on statistic characteristics of probability map is proposed in this paper. The method uses the probability map to reflect whether the image has been processed by content-aware resizing operation. And the proposed integral projection and local statistic characteristics are used to detect the tampered image. Then trained by classifier, this method can identify the content-aware resizing forgery more effectively. The experiment result reveals that the CFA(Color Filter Array) features detection algorithm can distinguish between original images and manipulation images with high detection accuracy. |
| |
| Keywords: | content-aware resizing statistic characteristics probability map image forgery |
|
| 点击此处可从《软件学报》浏览原始摘要信息 |
|
点击此处可从《软件学报》下载全文 |
|
