Search

Steganalysis technique is the way of detecting stego and cover image which satisfies the needs of individuals and public security communication. But now a days it has become a powerful tool for criminals engaged in crime activities. So steganalysis is required for preventing these crime activities and also to measure the performance level of various steganography tools. In this paper, a modified steganalysis method is proposed for detecting stego image and cover image through prediction error image generation, transformation, feature extraction and classification process. During the generation of prediction error image a GAP(Gradient Adjusted predictor) is used to getbetter detection rate. Then three order haar wavelet transform is performed on the image itself and its prediction error image to get twelve wavelet subbands. Moreover, decomposition of first scale diagonal subband is also applied to get four extra subbands. In the feature extraction process, first three order moments of characteristic function of wavelet subbands (including image itself & its prediction error image) are selected to form the feature vectors. Finally, the classification task is performed to classify into cover and stego images using ANN. The method is evaluated for various steganography tools such as StegJ, Openstego, Image Steganography and invisible Secret. The detection rate of the propose steganalyzer is 75-90% and improvement is 5-20.3% using ANN. It also shows that the detection rate of the propose steganalyzer is 60-87% and improvement is 1-19.7% using SVM.