Dingjie Xu, Na Ren, Changqing Zhu
Existing zero-watermarking algorithms for remote sensing images heavily rely on traditional feature extraction techniques, which are vulnerable to targeted attacks and lack discriminability for images captured by different sensors or at different time periods in the same geographical area. To address these limitations, this paper proposes a novel watermarking algorithm based on blockchain and Stacked Denoising Autoencoder (SDAE) to achieve lossless copyright protection for high-resolution remote sensing images (HRRS). The algorithm utilizes SDAE to extract deep and robust features from local square feature regions (LSFR) for watermark construction. Moreover, the algorithm incorporates a watermark registration scheme designed with Hyperledger Fabric and IPFS to ensure secure and trustworthy registration of watermarks and associated parameter information, enhancing the algorithm's uniqueness. Experimental results demonstrate the effectiveness of the proposed algorithm against various watermark attacks and its high discriminability for similar images. This algorithm holds significant potential for wide-ranging applications in the field of lossless copyright protection for HRRS, effectively safeguarding the commercial interests of data providers.