Still image steganography detection based on machine learning techniques

In the last two decades, steganalysis has become a fertile research area to minimize the security risks left behind by misuse of data concealment in digital computer files. As the propagation of hidden writing increased, the need for the steganalysis emerged and grew to a large extent necessary to deter illicit secret communications. This thesis introduces a steganalysis system to detect hidden information in still images through using co-occurrence matrix, frequency domain transforms, the first three moments, and Back Propagation Neural Network (BPNN). Firstly, the co-occurrence matrix is calculated for the input image, which suspected to be a carrier of hidden secret information. Second, three levels of Discrete Wavelet Transform (DWT) are applied resulting in 12 subbands. Then, those subbands along with the original image are transformed by Discrete Fourier Transform (DFT) or Discrete Cosine Transform (DCT) to produce 13 subbands. After that, the first three moments are calculated resulting feature vector with 39 feature. Finally, a BPNN is used as a classifier to determine whether the image is containing hidden information or not. The proposed approach is tested with and without co-occurrence matrix, each of them once using DFT and another time using DCT. The results showed that using the co-occurence matrix with DFT has the highest performance compared to previous studies.