基于多分类的QDCT域大容量H.264/AVC视频信息隐藏算法

Multi-classification information hiding algorithm for H.264/AVC video with high capacity in QDCT domain

提出了一种在开环外的量化离散余弦变换(QDCT)系数上的H.264视频信息隐藏算法。在抑制漂移失真的条件下,对邻块所需参考像素进行多组分类。其次,充分挖掘帧内4×4亮度可用QDCT系数对,结合9进制方向调整(EMD)嵌入算法和矩阵编码,实现秘密信息的高容量嵌入。同时,通过最多修改一组QDCT系数保证了含密视频的质量。此外,本文的信息提取算法不需要对含密视频完全解码,只需得到QDCT系数和帧内预测模式,即可完全提取秘密信息。实验结果表明,本文算法在大幅度提高嵌入容量的同时,对比特率和视频的质量影响不大。

An information hiding scheme is proposed based on quantized discrete cosine transform （QDCT） coefficient of open loop for H. 264 video in this paper. Under the condition of averting the distortion drift,the reference pixels of the adjacent blocks are classified into multi groups. Then, 9-ary exploiting modification direction （EMD） embedding algorithm and matrix coding are used to obtain high hiding capacity by fully exploiting the available QDCT coefficient-pairs of the 4X4 blocks in frames. At the same time,the quality of stego-video can be ensured by changing at most a set of QDCT coefficients. Furthermore,the detection of hidden information only requires to decode the intra QDCT coefficients and intra-prediction mode without decoding the video completely. The secret information can be extracted completely. Experimental results show that the proposed method can greatly improve the capacity of hid- den information, and also has little effect on the bit rate and quality of video.