CASIA OpenIR  > 智能感知与计算研究中心
Local correlation pattern for image steganalysis
Xu, Xikai; Dong, Jing; Wang, Wei; Tan, Tieniu
2015
会议名称IEEE China Summit and International Conference on Signal and Information Processing
会议录名称Proceedings of IEEE China Summit and International Conference on Signal and Information Processing
会议日期12-15 July 2015
会议地点Chengdu, China
摘要Correlation of pixels is the most important information used for image steganalysis. Current methods often consider some special types of relationships among neighboring pixels. In this paper, we propose a general descriptor to consider the correlation of pixels comprehensively. We consider the correlation of pixels in an adjacency pattern as a local correlation pattern (LCP). The LCP descriptor is proposed to embrace different local correlation patterns and represent each pattern by mapping the relative values of pixels in the pattern to a numerical value. Then, histograms of LCP values are taken as features for steganalysis. The LCP descriptor also can be used for describing the correlation of elements in the residual image obtained by image filtering. Experiments show that our constructed feature set based on the LCP descriptor outperforms a state-of-the-art method on detecting three popular steganographic algorithms.
关键词Steganalysis Local Correlation
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12312
专题智能感知与计算研究中心
通讯作者Dong, Jing
推荐引用方式
GB/T 7714
Xu, Xikai,Dong, Jing,Wang, Wei,et al. Local correlation pattern for image steganalysis[C],2015.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
07230446.pdf(420KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Xu, Xikai]的文章
[Dong, Jing]的文章
[Wang, Wei]的文章
百度学术
百度学术中相似的文章
[Xu, Xikai]的文章
[Dong, Jing]的文章
[Wang, Wei]的文章
必应学术
必应学术中相似的文章
[Xu, Xikai]的文章
[Dong, Jing]的文章
[Wang, Wei]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 07230446.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。