查询结果:   李皓,张兴忠.基于球哈希和改进的灰度差算法的视频拷贝检测[J].计算机应用与软件,2016,33(1):181 - 184,189.
中文标题
基于球哈希和改进的灰度差算法的视频拷贝检测
发表栏目
图像处理与应用
摘要点击数
724
英文标题
VIDEO COPY DETECTION BASED ON SPHERICAL HASHING AND IMPROVED GRAY DIFFERENCE ALGORITHM
作 者
李皓 张兴忠 Li Hao Zhang Xingzhong
作者单位
太原理工大学计算机科学与技术学院 山西 太原 030024     
英文单位
College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan 030024,Shanxi,China     
关键词
版权保护 视频拷贝检测 灰度差 SIFT特征 球哈希
Keywords
Copyright protection Video copy detection Gray difference SIFT feature Spherical Hashing
基金项目
国家科技支撑项目子课题(2012BAH0 4F02-2);山西省国际科技合作项目(2012081034-2);人社部留学人员科技活动项目(2011-508)
作者资料
李皓,硕士生,主研领域:计算机视觉,图像处理,模式识别。张兴忠,副教授。 。
文章摘要
针对大规模的视频版权保护中检索准确率低和检索速度慢的问题,提出一种基于球哈希和改进的灰度差算法的视频拷贝检测方法。首先,对传统的灰度差提取关键帧的算法进行改进,提出利用灰度差与灰度差累积量相结合的方法提取关键帧,减少了提取关键帧时产生的累积误差,提高视频检索的准确率;然后,提取关键帧的SIFT特征,并且利用著名的球哈希算法对SIFT特征建立索引,把128维的高维浮点向量变为二值索引,提高检索速度。实验结果表明该方法不仅提高了视频检索的准确率和检索速度,而且保证了较高的查全率。
Abstract
For the problem of low retrieval accuracy and slow retrieval speed in large-scale video copyright protection, we proposed a video copy detection method, it is based on spherical Hashing and improved gray difference algorithm. First, we improved the traditional algorithm of extracting key frames based on gray difference, proposed a method to extract key frames which combines the gray difference with gray difference accumulation, thus reduced the cumulative errors when extracting key frames, as well as improved the accuracy of video retrieval. Secondly, we extracted the SIFT feature of key frames and used the famous spherical Hashing algorithm to establish hashing index for SIFT feature, and converted the 128 high-dimensional floating-point vectors to binary hashing indexes, therefore improved retrieval speed. Experimental results showed that this method not only improved video retrieval accuracy and retrieval speed, but also ensured a higher recall rate.
下载PDF全文