Robust video hashing based on representative-dispersive frames

This study proposes a robust video hashing for video copy detection. The proposed method, which is based on representative-dispersive frames (R-D frames), can reveal the global and local information of a video. In this method, a video is represented as a graph with frames as vertices. A similarity measure is proposed to calculate the weights between edges. To select R-D frames, the adjacency matrix of the generated graph is constructed, and the adjacency number of each vertex is calculated, and then some vertices that represent the R-D frames of the video are selected. To reveal the temporal and spatial information of the video, all R-D frames are scanned to constitute an image called video tomography image, the fourth-order cumulant of which is calculated to generate a hash sequence that can inherently describe the corresponding video. Experimental results show that the proposed video hashing is resistant to geometric attacks on frames and channel impairments on transmission.