Robust video hashing based on representative-dispersive frames  

作　　者：NIE XiuShan LIU Ju SUN JianDe WANG LianQi YANG XiaoHui 

机构地区：[1]School of Information Science and Technology,Shandong University of Finance and Economics [2]School of Information Science and Engineering,Shandong University [3]Hisense State Key Laboratory of Digital Multi-Media Technology [4]Department of Physics and Astronomy,University of California

出　　处：《Science China(Information Sciences)》2013年第6期212-222,共11页中国科学（信息科学）（英文版）

基　　金：supported partially by National Basic Research Program of China (973 Program) (Grant Nos.2009CB320905,2010CB735906);National Natural Science Foundation of China (Grant Nos. 61101162,61001-180);Cultivation Fund of the Key Scientific and Technical Innovation Project (Grant No. 708059)

摘　　要：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.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.

关 键 词：representative-dispersive frames video hashing video tomography video copy detection 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]