Feature extraction method and extraction system for digital image steganalysis

Abstract

The invention discloses a feature extraction method and extraction system for digital image steganalysis. The method comprises the steps of filtering a steganalysis feature image to be extracted by ten filters to obtain residual images, the ten filters including four non-directional filters and six directional filters; encoding the residual images according to an LBPriu2 model and / or a DLBP model to obtain coding graphs, obtaining second-order co-occurrence matrices in four different directions according to the coding graphs, and for the six directional filters, adding the co-occurrence matrices calculated in different directions; for the calculated co-occurrence matrices, combining the co-occurrence matrices in different directions and decreasing the dimensions of the co-occurrence matrices, and then performing LOG function mapping to obtain co-occurrence matrix features. According to the invention, similar performance to the existing mainstream general steganalysis method SRM is gained, and the classification effect has higher accuracy than that of the SRM.

Description

technical field [0001] The invention relates to the technical field of digital image steganalysis, in particular to a digital image steganalysis feature extraction method and extraction system. Background technique [0002] There are two types of digital image steganalysis: active steganalysis and passive steganalysis. Passive steganalysis mainly judges whether the carrier hides secret information, while active steganalysis needs to estimate whether the carrier has secret information. The parameters of the steganographic algorithm further extract the secret information. According to usage scenarios, steganalysis is divided into special steganalysis and general steganalysis. The general steganography method needs to detect a variety of steganographic algorithms. Its operation process is mainly divided into two parts: feature extraction and classifier classification. Among them, the feature design part is the main content of the research and the algorithm function link of thi...

AI Technical Summary

Problems solved by technology

The local binary model (LBP) is an operator that combines structure and statistics. Its histogram features are well applied in image texture classification. Using the local binary model histogram features in spatial steganalysis Some effects have been achieved, but its performance is still inferior to SRM. The histogram feature is insufficient to express the correlation between image pixels, and it is difficult to capture the changes in image statistical characteristics brought about by steganography. In addition, the definition of LBP and the problem of steganalysis are not directly matched. is also its shortcoming

Images