Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (7): 2070-2075.DOI: 10.11772/j.issn.1001-9081.2020081177

Special Issue: 多媒体计算与计算机仿真

• Multimedia computing and computer simulation • Previous Articles     Next Articles

Video similarity detection method based on perceptual hashing and dicing

WU Yue1,2, LUO Jiangtao2, LIU Rui1,2, HU Zhongyin1   

  1. 1. School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
    2. Electronic Information and Networking Research Institute, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Received:2020-08-06 Revised:2020-10-20 Online:2021-07-10 Published:2020-12-09

基于感知哈希和切块的视频相似度检测方法

吴悦1,2, 雒江涛2, 刘锐1,2, 胡钟尹1   

  1. 1. 重庆邮电大学 通信与信息工程学院, 重庆 400065;
    2. 重庆邮电大学 电子信息与网络工程研究院, 重庆 400065
  • 通讯作者: 雒江涛
  • 作者简介:吴悦(1997-),女,重庆人,硕士研究生,主要研究方向:机器视觉;雒江涛(1971-),男,河南郑州人,教授,博士生导师,博士,主要研究方向:移动大数据、新一代网络技术、通信网络测试与优化;刘锐(1995-),男,重庆人,硕士研究生,主要研究方向:机器视觉;胡钟尹(1999-),女,重庆人,主要研究方向:机器视觉。

Abstract: For a long time, video copyright infringement problems have emerged one after another, and the detection of video similarity is an important approach of identifying video copyright infringement. Concerning the problems of the correlation difficulty of multi-feature relation and high time complexity in the existing video similarity detection methods, a fast comparison method based on perceptual hashing and dicing was proposed. First, the key image frames of the video were used to generate a digital fingerprint set. Then, based on the dicing method, the corresponding inverted index was generated to speed up the comparison between digital fingerprints. Finally, the similarity was judged according to the obtained Hamming distance between the digital fingerprints. Experimental results show that the proposed method can reduce the detection time by an average of 93% with ensuring the detection accuracy compared to the traditional perceptual hashing comparison methods; in the comparison with three common methods including Multi-Feature Hashing (MFH), Self-Taught Hashing (STH) and SPectral Hashing (SPH), the mean Average Precision (mAP) of the proposed method is increased by 1.4%, 2% and 2.3%,respectively, and the detection time is shortened by 25%, 32% and 16%, respectively, which verifies the feasibility of the proposed method.

Key words: video similarity, perceptual hashing, dicing, digital fingerprint, inverted index

摘要: 长期以来视频侵权问题层出不穷,而检测视频相似度是视频侵权的重要手段。针对现有视频相似度检测方法中存在的多特征关系难以关联、时间复杂度高等问题,提出一种基于感知哈希和切块的快速对比方法。首先,利用视频的关键图像帧生成数字指纹集;然后,基于切块的方法构建相应的倒排索引,提高数字指纹间的对比速度;最后,根据得到的数字指纹间的汉明距离进行相似度判定。实验结果表明,与传统的感知哈希对比方法相比,该方法能在保证检测准确度的前提下将检测时间平均缩短93%;与多特征哈希(MTH)、自学习哈希(STH)、光哈希(SPH)等三种常见方法相比,所提方法的平均准确率均值(mAP)分别提高了1.4%、2%和2.3%,检测时间分别缩短了24%、32%和16%,验证了所提方法的可行性。

关键词: 视频相似度, 感知哈希, 切块, 数字指纹, 倒排索引

CLC Number: