网络与信息安全学报 (Jun 2023)
Image double fragile watermarking algorithm based on block neighborhood
Abstract
To address the security risks associated with fixed offset mapping in self-embedded watermarking technology, as well as the limited recovery rate of single watermarking methods, an image double fragile watermarking algorithm based on block neighborhood was proposed.The image was divided into non-overlapping blocks of size 4×4 and block truncation coding was used to generate the recovery watermark based on the image block.For each image block, a neighborhood of a proper size was specified and two mapping blocks were randomly selected from the regions within and outside the neighborhood.Then the recovery watermark was embedded into the two mapping blocks simultaneously.The image block neighborhood setting mechanism of the algorithm ensured that the image block maintains a certain distance from its corresponding mapping block.Additionally, the selection mechanism of mapping blocks inside and outside the image block neighborhood ensured a certain distance between the two mapping blocks, thereby guaranteeing the security of the watermark.In the case of continuous region tampering, the relationship between the tampered region and the neighborhood of the image block was analyzed theoretically.The analysis showed that a suitable image block neighborhood can improve the average recovery rate of the tampered area compared with the random mapping embedding algorithm.Besides, the distribution trend of the average recovery rate of the tampered area and the recovery rate of each image block in the tampered area were given by numerical calculation.It was found that the tampered area image block can be recovered 100%, some image blocks in the center of the tampered area can be recovered 100%, and the recovery rate of image blocks in tampered area will be reduced.The experimental results verify the rationality and effectiveness of the theoretical analysis.Moreover, when the neighborhood parameters are large, the proposed algorithm achieves a higher average recovery rate of the tampered region than the random mapping embedding algorithm in the case of continuous region tampering.
