Steganographic detection in image using the reduction of support vectors

摘要

Steganography is the technique for hiding secret information in other data such as still, multimedia images, text, and audio. The steganalysis is the reverse technique in which detection of the secret is done in the stego image. The contourlet transform is a new two dimensional extension of the wavelet transform using multi-scale and directional filter banks. In this paper, we propose a new universal steganalysis method for JPEG images based upon hybrid transform features (cosinus discrete and contourlet transform). Then the detection is usually cast as classification problem, we used kernel-based methods for the reducting of the computational cost of classification, by using linear algebra of a kernel Gram matrix of the support vectors (SVs) low computational cost. The pruning is based on the evaluation of the performance of the classifier which is formed by the reduced SVs in SVM. The feasibility of the evaluation criterion and the effectiveness of the proposed method are demonstrated.