Title: DCT statistics and pixel correlation-based blind image steganalysis for identification of covert communication
Authors: Madhavi B. Desai; S.V. Patel; Vipul H. Mistry
Addresses: Computer Science and Engineering Department, R.N.G. Patel Institute of Technology, Bardoli, Gujarat, India ' MCA Department, Sarvajanik College of Engineering and Technology, R.K. Desai Marg, Opp. Mission Hospital, Athwalines, Surat, 395001, Gujarat, India ' Electronics and Communication Engineering Department, S.N.P.I.T & R.C, Umrakh, Gujarat, India
Abstract: The interconnection of systems through networks, access to information, computer technologies and furtherance of image steganography techniques exploited to send secret information on social network builds the requisite of image steganalysis. Existing image steganalysis methods are either domain specific or the one which requires large dimensional feature set. Considering the types of image steganography methods, embedding rates, image types and feature dimensionality there is an utmost need of a low dimensional blind image steganalysis method. This paper proposes a 32-D DCT statistics and pixel correlation (DSPC) based blind image steganalysis algorithm with the aim to the reduced time complexity of feature extraction as well as the complexity of classifier. The performance of the proposed algorithm is evaluated using experiments with varying embedding message size, message types and image formats using ensemble classifier. The algorithm is implemented in MATLAB and all the experiments are performed on BSDS300 and CorelDraw image datasets.
Keywords: blind image steganalysis; binary similarity measures; ensemble classifier; DCT transform; feature extraction; statistical features; SVM.
International Journal of Computational Intelligence Studies, 2020 Vol.9 No.4, pp.336 - 354
Received: 31 Jul 2018
Accepted: 21 Feb 2019
Published online: 16 Oct 2020 *