提出了一种基于遗传算法的自适应半脆弱图像水印方法,该方法要求水印对常见的操作具有鲁棒性,如JPEG 压缩,而对其他的一些恶意操作具有脆弱性。 根据图像局部区域的类型自适应地确定了水印的嵌入强度,用 GA 来优化了水印的嵌入位置。 仿真结果表明,方法不会影响图像的主客观质量,而且可嵌入的水印信息量大。 更为重要的是,方法可以准确确定恶意攻击的位置,显示了相比于其他方法的优越性。

A new semi-fragile digital image watermarking method based on genetic algorithm was proposed. This method requires the watermark robust to common operations such as JPEG compression, and be fragile to other malicious actions. The embedding strength of the watermark was determined adaptively based on the type of image local region and GA was used to optimize the location of the embedded watermark. Simulation results proved that the proposed method has no influence on the objective and subjective quality of the image and the watermark can embed large amount of information; more importantly, the method proposed can exactly accurately determine the location of the malicious attacks, which demonstrates its superiority over the other methods.