Authors:
Yin Zhang
;
Zengxiang Lu
and
Haiming Lu
Affiliation:
Tsinghua University, China
Keyword(s):
H.264 compressed video, adaptive watermarking, block classification, real-time, drift compensation.
Related
Ontology
Subjects/Areas/Topics:
Authentication and Watermarking
;
Multimedia
;
Multimedia Systems and Applications
;
Telecommunications
Abstract:
Focusing on the problem that watermark can cause visible image distortions in some plain areas, an adaptive watermarking algorithm for H.264 is proposed. To embed watermark quickly, we directly operate in the DCT domain. For high imperceptibility, we classify the blocks based on Human Visual System (HVS). However, most current classification methods are not suitable for H.264 compressed domain because the DCT coefficients residue cannot reflect the texture activity accurately due to the employment of intra-prediction. A new block classification method is applied, in which we make restriction during the encoding process so that the 4×4 blocks can be classified into plain, edge and texture blocks according to the intra-prediction mode and quantized integer DCT coefficients in compressed domain. It is effective in block classification and realizes good adaptive performance for watermarking. Drift compensation is also accomplished in our watermarking algorithm. The experimental results d
emonstrate our watermarking method can achieve both large capacity and good image imperceptibility. Additionally, the method is simple and appropriate for real-time applications.
(More)