A robust video hash scheme based on 2D-DCT temporal maximum occurrence

In this paper, we propose a video hash scheme that utilizes image hash and spatio-temporal information contained in video to generate video hash. A video clip is firstly segmented to shots, and video hash is derived in unit of shot. We notice that for video hash applications in identification and verification, reference video and suspected video always appear in pair. Therefore, we propose to derive the shot hash in a pairwise manner. For both reference and suspected shot, we apply 2-Dimensional Discrete Cosine Transform (2D-DCT) to each frame in the shot, quantize the Discrete Cosine Transform (DCT) coefficient, and record the temporal occurrence of the co-located coefficient. We then choose a pair of the closet value as the DCT coefficient for every collocated entry, inverse transform to the spatial domain, and derive image hashes from two feature frames by hash based on Radial projections (Radial hASH). Experiment results show that the proposed 2D-DCT temporal maximum occurrence (2D-DCT TMO) scheme successfully derives shot hash that represents the content, and is very robust in video identification, authentication, and verification.