Title: Image steganalysis: real-time adaptive colour image segmentation for hidden message retrieval and Matthew's correlation coefficient calculation

Authors: B. Yamini; R. Sabitha

Addresses: Department of Computer Science and Engineering, Sathyabama University, Chennai-119, Tamil Nadu, India ' Department of Computer Science and Engineering, Jeppiaar Institute of Technology, Kunnam, Sriperumbudur, Chennai – 631604, Tamil Nadu, India

Abstract: Adaptive image steganography is the method of hiding secret information in colour adaptive regions of the image. Its counter method to reveal hidden secret information is called as adaptive image steganalysis. In the proposed method, the colour correlations between pixels are used to identify the adaptive region of the image by real time adaptive colour image segmentation. Bi-cubic interpolation method is applied on these colour adaptive regions to extract the features from the selected region. These features are considered for classification using support vector machine classifier, to distinguish between stego and cover images. Reversible two least significant bit (LSB) technique is used to identify and to retrieve the hidden content from the payload locations. The accuracy is measured using Matthew's correlation coefficient calculation. The results of real-time adaptive colour image segmentation outperform the methods, normalised cut segmentation, MX-quadtree segmentation and watershed segmentation.

Keywords: adaptive steganalysis; steganography; stego images; F-score; Matthew's correlation coefficient; bi-cubic interpolation method; reversible two LSB; support vector machine; SVM.

DOI: 10.1504/IJICS.2022.121292

International Journal of Information and Computer Security, 2022 Vol.17 No.1/2, pp.83 - 103

Received: 09 Oct 2017
Accepted: 26 Jan 2019
Published online: 04 Mar 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article