Image Forgery Forensics Based on Manual Blurred Edge Detection

摘要：

In this paper, a novel image forensics method is proposed to detect manual blurred edges from a tampered image. Firstly, the image edges are analyzed by using nonsubsampled contourlet transform. Then the differences between the normal edge and the blurred edge are extracted by researching phase congruency and prediction-error image. After that, the features are used to train the SVM, by which the blurred edges can be distinguished. Finally, the local definition is introduced to indicate the differences between the manual blur and defocus ones. Experimental results show that this method can detect possible blurring in images and locate the tampering boundary with a relative high accurate rate.

关键词： Non-subsampled Contourlet Image Forensics Phase Congruency Blur Local Definition

作者: Junwen Wang Guangjie Liu Bo Xu Hongyuan Li Yuewei Dai Zhiquan Wang

作者单位: School of Automation Nanjing University of Science & Technology Nanjing, China

会议类型: 国际会议

会议名称: 2010年IEEE多媒体信息网络与安全国际会议

会议地点: 南京

会议语种:英文

页码: 907-911

在线出版日期: 2010-11-01（万方平台首次上网日期，不代表论文的发表时间）