基于GoogLeNet-GMP网络的自适应图像水印方法

Adaptive image watermarking method based on GoogLeNet-GMP network

为提高水印方案的抗攻击能力和自适应性,提出一种盲水印的GoogLeNet-GMP神经网络方案。首先,所提网络较为简约,最深的路径(即通过预处理网络、嵌入网络和提取网络的路径)仅包含17层。通过在水印预处理网络中提高水印分辨率来保持宿主图像的分辨率,由此增强了水印的透明性。同时,在水印预处理网络中使用平均池化,将水印数据的二进制值与宿主图像结合在一起,从而增强了水印的透明性。最后,提取器使用交叉熵作为损失函数,实现嵌入器和提取器之间的训练平衡。实验结果表明,所提方案性能出色,水印容量为0.003 8,数据集中的PSNR均值为40.57 dB。在有意义攻击下的性能优于其他先进方法。

To improve the anti attack ability and adaptability of the watermarking scheme, a blind watermarking scheme based on GoogLeNet-GMP is proposed. Firstly, the proposed network is relatively simple, and the deepest path(that is the path through preprocessing network, embedding network and extracting network) only contains 17 layers. The resolution of the host image is maintained by increasing the watermark resolution in the watermark preprocessing network, thus enhancing the transparency of the watermark. The average pooling is used in the watermark preprocessing network to combine the binary value of the watermark data with the host image properly, so it can enhance the transparency of the watermark. Finally, The extractor uses cross entropy as the loss function to achieve the training balance between the embeder and the extractor. The experimental results show that the performance of the proposed scheme is excellent, the watermark capacity is 0.003 8, and the average PSNR in the dataset is 40.57 dB. The performance under meaningful attack is better than other advanced methods.