[1]文振焜,高金花,杜以华,等.鲁棒可区分的压缩视频感知哈希算法研究[J].深圳大学学报理工版,2013,30(No.2(111-220)):157-161.[doi:10.3724/SP.J.1249.2013.02157]
　Wen Zhenkun,Gao Jinhua,Du Yihua,et al.Robust and discriminative perceptual hash algorithm in compressed video[J].Journal of Shenzhen University Science and Engineering,2013,30(No.2(111-220)):157-161.[doi:10.3724/SP.J.1249.2013.02157]
点击复制

鲁棒可区分的压缩视频感知哈希算法研究()
分享到：

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第30卷
期数:
2013年No.2(111-220)
页码:
157-161
栏目:
电子与信息科学
出版日期:
2013-03-18

文章信息/Info

Title:
Robust and discriminative perceptual hash algorithm in compressed video
作者:
文振焜1; 高金花2; 杜以华1; 朱映映1; 刘朋飞1
1）深圳大学计算机与软件学院，深圳 518060
2）深圳信息职业技术学院机电工程学院，深圳 518172
Author(s):
Wen Zhenkun1;  Gao Jinhua2;  Du Yihua1;  Zhu Yingying1;  and Liu Pengfei1
1) College of Computer Science and Software, Shenzhen University, Shenzhen 518060, P.R.China
2) Mechanical and Electronic Engineering, Shenzhen Institute of Information Technology, Shenzhen 518172, P.R.China
关键词:
视频处理; 感知哈希; 小波分析; 独立分量分析量化; 视频压缩; 视频版权; 视频安全; 视觉感知; 视频篡改检测与定位
Keywords:
video processing;  perception hash;  wavelet analysis;  independent component analysis quantization;  video compression;  video copyright;  video security;  visual perception;  video tamper detection and location
分类号:
TN 911.73
DOI:
10.3724/SP.J.1249.2013.02157
文献标志码:
A
摘要:
运用比较宏块互异数方法得到视频关键帧，提出基于Gabor小波分解的视频感知特征快速提取算法，针对小波分解后得到的特征矩阵，给出基于负熵目标函数的FastICA优化降维量化策略，并运用中位值量化方法得到哈希位串．采用标准格式视频验证的结果显示，该算法对亮度变化、噪音污染等常规内容操作具有良好的鲁棒性能，对感知内容不同的视频序列也有较好的区分性能. 研究成果可为视频版权、视频安全和视频篡改检测提供理论支撑和技术支持．
Abstract:
By obtaining video key frames according to the number of distinct macro-blocks, a fast Gabor-wavelet-decomposition based feature extraction algorithm for video perception was proposed. To handle the feature matrix of wavelet decomposition, a dimensional reduction and quantization strategy using FastICA optimization was put forward based on the objective function of negative entropy. Meanwhile the Hash bunch is attained with medium value quantization. The test results on videos of standard format demonstrate that the algorithm performs robustly against regular operations such as brightness variations and noise pollution. It also shows good performance in distinguishing video sequences of different perception contents. The result of the research can provide technical support in the areas of video copyright, video security, tamper detection of video, etc.

参考文献/References:

［1］ Niu Xiamu，Jiao Yuhua．An overview of perceptual hashing［J］． Chinese Journal of Electronics，2008，36(7)：1405-1411．(in Chinese)
牛夏牧，焦玉华．感知哈希综述［J］．电子学报，2008，36(7)：1405-1411．
［2］ Mucedero A，Lancini R，Mapelli F．A novel hashing algorithm for video sequences［C］// Proceedings of the 2004 International Conference on Image Processing．Singapore：IEEE Press，2004，4：2239-2242．
［3］ De Roover C，De Vleeschouwer C，Lefebvre F，et al． Robust video hashing based on radial projections of key frames［J］．IEEE Transactions on Signal Processing，2005，53(10)：4020-4037．
［4］ Coskun B，Sankur B，Memon N．Spatio-temporal transform based video hashing［J］．IEEE Transactions on Multimedia，2006，8(6)：1190-1208．
［5］ Coskun B，Sankur B．Robust video hash extraction［C］// Proceedings of the 12th IEEE Signal Processing and Communications Applications Conference．Kusadasi(Turkey)：IEEE Press，2004：2295-2298．
［6］ Zhou Xuebing，Schmucker M，Brown C．Perceptual hashing of video content based on differential block similarity［C］// 2005 International Conference on Computational Intelligence and Security．Xi’an(China)：IEEE Press，2005，3802：80-85．
［7］ Oostveen J C，Kalker T，Haitsma J．Visual hashing of digital video：applications and techniques［C］// Proceedings of SPIE：Applications of Digital Image Processing XXIV．San Diego(USA)：SPIE Press， 2001，4472：121-131．
［8］ Zhang Hui，Zhang Haibin，Li Qiong． Image perceptual hash based on human visual system［J］． Chinese Journal of Electronics，2008，36(12A)：30-34．(in Chinese)
张慧，张海滨，李琼．基于人类视觉系统的图像感知哈希算法［J］．电子学报，2008，36(12A)：30-34．
［9］ Walk S, Majer N, Schindler K, et al.New features and insights for pedestrian detection［C］// IEEE Conference on Computer Vision and Pattern Recognition (CVPR)．San Francisco(USA)：IEEE Press，2010：1030-1037．
［10］ Ying Long, Xu Changsheng, Guo Wen. extended MHT algorithm for multiple object tracking［C］// ICIMCS ‘12 Proceedings of the 4th International Conference on Internet Multimedia Computing and Service．New York：ACM，2012：75-79．
［11］ Pu Yungong． Research on the Algorithm for Video Key Frame Extraction in Compressed Domain［D］．Beijing：Beijing Jiaotong University，2009．(in Chinese)
普云功．基于压缩域的视频关键帧提取算法研究［D］．北京：北京交通大学，2009．
［12］ Wen Zhenkun，Zhu Weizong，Ouyang Jie． A robust and discriminative video perceptual hash algorithm［C］// The 18th China Conference on Multimedia．Xi’an(China)：Tsinghua University Press，2009：38-43．(in Chinese)
文振焜，朱为总，欧阳杰．一种鲁棒可区分的视频感知哈希算法［C］// 第18届全国多媒体学术会议论文集．西安(中国)：清华大学出版社，2009：38-43．
［13］ Hamon K，Schmuker M，Zhou Xuebing．Histogram-based perceptual hashing for minimally changing video sequence［C］// The 2nd IEEE International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution．Darmstadt(Germany)： IEEE Press，2006：236-241．

备注/Memo

备注/Memo:
Received：2011-06-27；Revised：2012-08-10；Accepted：2013-02-28
Foundation：National Natural Science Foundation of China (61170326)；Shenzhen Technology Research Foundation for Basic Project（JC201005250052A）
Corresponding author：Professor Wen Zhenkun．E-mail: wenzk@szu.edu.cn
Citation：Wen zhenkun, Gao Jinhua, Du Yihua，et al．Robust and discriminative perceptual hash algorithm in compressed video［J］. Journal of Shenzhen University Science and Engineering, 2013, 30(2): 157-161.（in Chinese）

基金项目：国家自然科学基金资助项目(61170326);深圳市科技基础研究基金资助项目(JC201005250052A)
作者简介：文振焜(1962-)，男(汉族)，深圳大学教授．E-mail：wenzk@szu.edu.cn
引文：文振焜，高金花，杜以华，等．鲁棒可区分的压缩视频感知哈希算法研究［J］. 深圳大学学报理工版，2013，30（2）：157-161.
更新日期/Last Update: 2013-03-19