Xiao Shaozhang, Zuo Xingyuan, Zhang Zhengwei, Li Fenfen
Faculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huai'an, Jiangsu 223003, China.
Math Biosci Eng. 2022 Jan;19(2):1108-1127. doi: 10.3934/mbe.2022051. Epub 2021 Nov 30.
Aiming at solving the problems of bad imperceptibility and low embedding rate of existing algorithms, a novel large-capacity reversible image watermarking based on improved difference expansion (DE) is proposed. Firstly, the smoothness calculation algorithm is used to calculate and sort the smoothness values of the divided image sub-blocks; then, the scrambled watermark is embedded into the sub-blocks with less smoothness after removing the abrupt point by using the generalized difference expansion (GDE); finally, the absolute difference operation is applied to the generated overflow pixels to make their pixel values within a reasonable range for embedding watermark information. Under the premise of ensuring a certain visual quality, multiple watermark embedding can effectively improve the embedding rate. The simulation results show that this algorithm not only realizes blind extraction, but also recovers the original images without loss. At the same time, this algorithm achieves a high embedding rate (the average embedding rate is as high as 77.91 dB) without decreasing the visual quality.
针对现有算法不可感知性差、嵌入率低的问题，提出了一种基于改进差分扩展（DE）的新型大容量可逆图像水印算法。首先，利用平滑度计算算法对分割后的图像子块的平滑度值进行计算和排序；然后，通过广义差分扩展（GDE）去除突变点后，将加扰水印嵌入到平滑度较小的子块中；最后，对生成的溢出像素进行绝对差运算，使其像素值在合理范围内以嵌入水印信息。在保证一定视觉质量的前提下，多次水印嵌入可有效提高嵌入率。仿真结果表明，该算法不仅实现了盲提取，还能无损恢复原始图像。同时，该算法在不降低视觉质量的情况下实现了较高的嵌入率（平均嵌入率高达77.91 dB）。
