Universal steganalysis using contourlet transform

Abstract

This paper proposes a new universal steganalysis method based on contourlet transform with high detection rate. An important aspect of this paper is that it uses the minimum number of features in the transform domain and gives a better accuracy than many of the existing steganalysis methods. Only five features have been extracted from the contourlet transformed image and a back propagation neural network classifier has been used to classify whether the given image is stego image or cover. The efficiency of the proposed method is demonstrated through experimental results. Also its performance is compared with the state of the art wavelet based steganalyzer (WBS), Feature based steganalyzer (FBS) and Contourlet based steganalyzer (CBS). The results show significantly high performance of our method. © 2012 Springer-Verlag GmbH.