Skip to Main Content
We propose a novel technique for image/video authentication at the semantic level. This method uses statistical learning, visual object segmentation and classification schemes for semantic understanding of visual content. This system embeds either the classification output or the user annotated model labels into multimedia data as watermarks. A robust rotation, scaling, and translation public watermarking method is used for embedding. The authentication process is executed by comparing the classification result with the information carried by the watermark. This method leads the authentication system to learn the semantic content of multimedia data and performs the authentication task in the semantic level.