Visible to the public Compressive Sensing Based Feature Residual for Image Steganalysis Detection

TitleCompressive Sensing Based Feature Residual for Image Steganalysis Detection
Publication TypeConference Paper
Year of Publication2017
AuthorsZhao, H., Ren, J., Pei, Z., Cai, Z., Dai, Q., Wei, W.
Conference Name2017 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)
ISBN Number978-1-5386-3066-2
KeywordsBCS measurement matrix, block CS measurement matrix, composability, compressed sensing, compressive sensing, compressive sensing based feature residual analysis, Databases, directional lifting wavelet transform, discrete wavelet transforms, DLWT coefficients, feature extraction, Feature residual, gaussian distribution, generalized Gaussian distribution model, GGD model, grayscale image processing, image colour analysis, image content feature analysis, Image detection, image representation, image steganalysis detection, matrix algebra, Metrics, privacy, pubcrawl, Sparse matrices, Sparse Representation, steganalysis, steganalytic method, steganography, steganography detection, wavelet transforms
Abstract

Based on the feature analysis of image content, this paper proposes a novel steganalytic method for grayscale images in spatial domain. In this work, we firstly investigates directional lifting wavelet transform (DLWT) as a sparse representation in compressive sensing (CS) domain. Then a block CS (BCS) measurement matrix is designed by using the generalized Gaussian distribution (GGD) model, in which the measurement matrix can be used to sense the DLWT coefficients of images to reflect the feature residual introduced by steganography. Extensive experiments are showed that proposed scheme CS-based is feasible and universal for detecting stegography in spatial domain.

URLhttps://ieeexplore.ieee.org/document/8276890/
DOI10.1109/iThings-GreenCom-CPSCom-SmartData.2017.168
Citation Keyzhao_compressive_2017