期刊名称:International Journal of Computer Science and Network Security
印刷版ISSN:1738-7906
出版年度:2010
卷号:10
期号:5
页码:73-81
出版社:International Journal of Computer Science and Network Security
摘要:Machine learning based steganalysis assume no information about stego image, host image, and the secret message. Many techniques have been proposed and new techniques are tried with different combinations to maximize the efficiency of retrieving hidden information. We have proposed a combination of polynomial preprocessed vector discriminant (PVD) with back propagation algorithm (BPA) neural network for steganalysis. Each set of pixel is preprocessed to obtain interpolated pixels to produce patterns using PVD. This is further trained by proposed neural network, adopted to obtain set of final weights. During implementation, the final weights are used to classify the presence of hidden information.