Image Splicing Detection Using Color Edge Inconsistency

摘要：

We propose a passive image splicing detection method based on consistency check of color distribution in the neighborhood of edge pixels. For a given image, we classify edges into different categories and extract shadow-shading-specular invariant edges as the candidate of splicing boundaries. Hue histogram entropy is then computed to capture abnormality of color distribution at these boundaries. Inconsistency of color distribution among different edge pixel neighborhood is used to localize the splicing boundary. Experiments show effectiveness of the method.

关键词： Passive forensics image splicing color edge detection

作者: Zhen Fang Shuozhong Wang Xinpeng Zhang

作者单位: School of Communication and Information Engineering Shanghai University Shanghai 200072, P.R. 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: 923-926

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）