Image retrieval and content integrity verification based on multipurpose image watermarking scheme

This paper presents a multipurpose image watermarking scheme which embeds robust and fragile watermarks in the wavelet domain for image retrieval and content integrity verification simultaneously. The proposed scheme consists of two main phases, the offline process and the online retrieval process. In the offline process, the feature vector is extracted from each image as the robust watermark to be embedded in the low frequency subband and a copyright signature is used as the fragile watermark to be embedded in the high frequency subband. The online retrieval process consists of three sub-processes, i.e., query feature computation, watermark extraction and feature vector matching. Since the features are embedded in the image data, it is unnecessary to compute the features but only to extract it from the watermarked image. A series of experiments are carried out on a watermarked image database and the simulation results demonstrate the advantages of the proposed watermarking scheme.