结合多级小波系数加权均值和量化的可公开敏感水印

传统水印通常对水印嵌入后掩体视觉质量较为关注,而对水印嵌入环节的安全性较为忽视,一些算法尽管提供了水印加密环节,但位置固定,导致嵌入水印易受攻击,而基于参数化小波的水印敏感性在实际中难以应用。针对以上问题,提出一种结合多级小波系数加权均值和量化的可公开敏感水印。在该算法中,首先将掩体图像的消息摘要算法5(MD5)值、用户密钥和初始参数与Logistic映射绑定,用于对水印加密和嵌入环节的多级小波系数进行随机选择;然后通过联合图像专家组(JPEG)压缩的各级小波系数绝对变化量的算术平均值来估算小波系数权重,调整小波系数加权均值以嵌入水印;最后通过孤立黑点滤除策略来提高水印提取质量。理论和实验表明,所提方法具有较好的明文敏感性和密钥敏感性,嵌入水印后图像峰值信噪比(PSNR)可达到45 dB,即使公开水印嵌入环节,嵌入的水印也难以篡改和提取,同时依然对图像剪裁、白噪声、JPEG压缩、覆盖和涂鸦等常规图像攻击具有鲁棒性。

Public sensitive watermarking algorithm with weighted multilevel wavelet coefficient mean and quantization

Conventional watermarking algorithms usually pay more attention to the visual quality of embedded carrier while ignore the security of watermarking. Although some methods provided watermarking encryption procedures, they usually embed watermarks in fixed positions which are prone to be attacked. The sensitivity of watermarking algorithm based on parameterized wavelet transform is difficult to be applied in practice. To address these problems, a public sensitive watermarking algorithm with weighted multilevel wavelet coefficient mean and quantization was proposed. In the proposed algorithm, firstly the Message Digest Algorithm 5 (MD5) value of cover image, user keys and initial parameters were bound with Logistic map which were used to encrypt watermarks and select wavelet coefficients in different decomposition levels; secondly weights of wavelet coefficients in different levels were estimated by absolute variation means of wavelet coefficients before and after Joint Photographic Experts Group (JPEG) compression, and then weighted multilevel wavelet coefficient mean was adjusted to embed watermark; finally an isolated black point filtering strategy was adopted to enhance the quality of fetched watermark. The experiments show the proposed method has better sensitivities of plaintext image and user keys and still is robust for common image attacks such as image clipping, white noise, JPEG compression, covering and graffiti. The Peak Signal-to-Noise Ratio (PSNR) of image after embedding watermarks can reach 45 dB. The embedded watermark is difficult to be tampered or extracted even if all watermarks embedding procedures are published.