image steganalysis based on co-occurrences of integer wavelet coefficients

we present a steganalysis scheme for lsb matching steganography based on feature vectors extracted from integer wavelet transform (iwt). in integer wavelet decomposition of an image, the coefficients will be integer, so we can calculate co-occurrence matrix of them without rounding the coefficients. before calculation of co-occurrence matrices, we clip some of the most significant bitplanes of the coefficients. by this preprocessing, in addition to reducing the dimension of feature vector the effects of the embedding are also preserved. we test our algorithm for different embedding rats using fisher linear discrimination (fld) classifier and by comparing it with the current state-of-the-art steganalyzers; it is shown that the proposed scheme outperforms them by significant margin.