Robust video fingerprinting based on visual attention regions

This paper presents a robust video fingerprinting based on visual attention regions. Video fingerprints, which are a set of short feature vectors, are unique to video clips and used for video identification. The performance of video fingerprinting is usually measured in terms of robustness and accuracy of identification. In our proposed approach, we extract video fingerprints using visual attention regions which remain the same for the perceptually same scenes with different types of distortions and different for different scenes. The experimental results show that the proposed video fingerprinting is effective for constructing video fingerprints that are robust against various content-preserving distortions and accurate in identifying different video clips.