Secure data hiding in binary document images for authentication

Abstract

In this paper, we present a data hiding algorithm for binary document images. This algorithm is based on the Distance-Reciprocal Distortion Measure that is used to evaluate the amount of distortion caused by flipping a particular pixel in binary document images. The pixels that will cause less distortion after flipping are preferred candidates for flipping. We do the embedding by enforcing the odd-even features of non-uniform blocks and employ a 2-D shifting to provide security for tamper proofing and authentication. Experiments show that the watermark-embedded document image has good quality and tampering of content can be detected successfully.

Publication
International Symposium on Circuits and Systems (ISCAS)
Haiping Lu
Haiping Lu
Director of the UK Open Multimodal AI Network, Professor of Machine Learning, and Head of AI Research Engineering

I am a Professor of Machine Learning. I develop translational multimodal AI technologies for advancing healthcare and scientific discovery.