基于纠错编码和RBF神经网络的盲水印新算法

A novel blind detection watermarking algorithm using error correction coding and RBF neural network

结合RBF神经网络和纠错编码技术,提出了一种把经过混沌加密的图像水印嵌入小波域,并实现盲检测的新型水印算法。首先,对原始图像进行小波分解得到各子带的小波系数;其次,通过密钥选择在小波系数中嵌入水印的起始位置,并对该小波系数进行量化处理作为RBF神经网络模型的输入值;最后,用混沌加密技术和纠错编码技术对待嵌入的水印信息进行预处理以增强水印系统的安全性和鲁棒性,把处理后的水印信息嵌入到经过RBF神经网络模型处理后的小波系数中。实验表明,该算法人类视觉掩蔽性良好,同时对于诸如JEPG压缩、椒盐噪声、滤波等常见图像处理攻击的鲁棒性达到了预期的效果。

Based on RBF neural network and error correction coding technology, a new blind detection watermarking algorithm which chaotic encrypted image watermark was embedded into the wavelet domain was proposed. Firstly, transform the original image using DWT transform and getting sub-band coefficient; Secondly, select the beginning position of watermark embedding coefficient using the secret key, quantize the DWT coefficient by quantized value and use the quantized result as the input value of RBF neural network; Finally, in order to improve the security and the robustness, the watermark was preprocessed by chaotic encryption and error correction coding technology, then the watermark information was embedded into the wavelet coefficients which was processed by RBF neural network model Experiment shows that the human visual masking of the algorithm is good, and achieving good robustness with common signal distortion such as JEPG compression, salt and pepper noise, filtering and other common image processing attacks.