Title: Textural features extraction for image integrity verification

Authors: Samia Boucherkha, Mohamed Benmohamed

Addresses: Computer Science Department, Vision and Infography Group, LIRE Lab, Mentouri University, Constantine 25000, Algeria. ' Computer Science Department, Vision and Infography Group, LIRE Lab, Mentouri University, Constantine 25000, Algeria

Abstract: Soft authentication intends to distinguish specific acceptable image manipulations from malicious ones. In this article, we propose a soft authentication scheme based on texture features and digital signature. It can detect and locate malicious manipulations made to individual image blocks, and verify the integrity of the overall image. It makes use of the invariance of second-order statistics on adjacent pixels to geometric transformations which are generally considered as content preserving modifications. A set of characteristics are extracted from each block, then processed to form a hash to be embedded in an other distant block. Furthermore, a cryptographic digital signature is incrementally formed, in a CBC manner to render the scheme resistant to content cutting and pasting attacks. Experimental results show the efficiency of the proposed scheme.

Keywords: data hiding; digital signature; features; image authentication; statistics; texture features; feature extraction; soft authentication; image integrity; image verification; cryptography; cutting and pasting attacks; malicious manipulation; image manipulation.

DOI: 10.1504/IJESDF.2008.020944

International Journal of Electronic Security and Digital Forensics, 2008 Vol.1 No.3, pp.268 - 280

Published online: 25 Oct 2008 *

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