Steganalysis of LSB Matching Based on Co-occurrence Matrix and Removing Most Significant Bit Planes

In this paper we present a novel LSB matching steganalysis method based on feature vectors derived from co-occurrence matrix in spatial domain, which is sensitive to data embedding process. This matrix is derived from an image that some of its most significant bit planes are removed. By this preprocessing in addition to decrease the size of feature vector also preserve effects of embedding. We investigate how LSB matching embedding effect more least significant bits and obtain better case for steganalysis. We use SVM for classification and our experimental results have demonstrated that the proposed scheme can increase detection rate of stegnalysis technique in attacking the LSB marching algorithm.