Universal steganalysis method based on multi-domain features

doi:10.12733/jics20101693

	Universal steganalysis method based on multi-domain features
	Yan, Yan; Li, Liting; Zhang, Qiuyu
刊名	Journal of Information and Computational Science
	2013-05-01
卷号	10 期号:7 页码:2177-2185
关键词	Algorithms Support vector machines Correlation coefficient Difference values Embedding capacity Embedding rates Mean and standard deviations Multi-domain features Statistical features Universal steganalysis
ISSN号	15487741
DOI	10.12733/jics20101693
英文摘要	A new method of universal steganalysis for BMP images, which had low embedding rate and based on multi-domain features, is proposed in this paper. It provided a way to extract statistical features from multi-domain for universal steganalysis and solved the problem of low detection rate for a small amount of data embedding. Features were extracted from gradient energy differences in spatial domain, correlation coefficient in DCT domain, and the mean and standard deviation of difference value matrix in DWT domain. Experiments results show that detection achieved a better reliability when the embedding capacity is above 2 KB, compared with existing methods. © 2013 by Binary Information Press.
语种	英语
出版者	Binary Information Press, Flat F 8th Floor, Block 3, Tanner Garden, 18 Tanner Road, Hong Kong
内容类型	期刊论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/112912]
专题	计算机与通信学院
作者单位	School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China
推荐引用方式 GB/T 7714	Yan, Yan,Li, Liting,Zhang, Qiuyu. Universal steganalysis method based on multi-domain features[J]. Journal of Information and Computational Science,2013,10(7):2177-2185.
APA	Yan, Yan,Li, Liting,&Zhang, Qiuyu.(2013).Universal steganalysis method based on multi-domain features.Journal of Information and Computational Science,10(7),2177-2185.
MLA	Yan, Yan,et al."Universal steganalysis method based on multi-domain features".Journal of Information and Computational Science 10.7(2013):2177-2185.