【24h】

Query by Example Video Based on Fuzzy C-Means Theory

机译:基于模糊C-均值理论的视频实例查询

获取原文
获取原文并翻译 | 示例

摘要

In this paper, a video retrieval strategy based on fuzzy c-means is presented for querying by example. Initially, the query video is segmented and represented by a set of shots, each shot can be represented by a key frame, and then video processing techniques are used to find visual cues to represent the key frame. Secondly, because the fuzzy c-means algorithm is sensitive to the initializations, we initialize the cluster center by the shots of query video, so that the users could achieve appropriate convergence. Each shot of query video is considered as a benchmark point in aforesaid cluster and each shot in the database possessed a class label. The similarity between the shots in the database having the same class label and the benchmark point can be transformed into the distance between them. Lastly, the similarity between the query video and the video in database is transformed into the number of similar shots. The experimental results demonstrate that the proposed approach can achieve good performance.
机译:本文提出了一种基于模糊c均值的视频检索策略,以实例查询。最初,将查询视频进行分割并由一组镜头表示,每个镜头可以由关键帧表示,然后使用视频处理技术来查找表示关键帧的视觉提示。其次,由于模糊c均值算法对初始化敏感,因此我们通过查询视频的镜头来初始化聚类中心,从而使用户可以实现适当的收敛。查询视频的每个镜头都被视为上述群集中的基准点,数据库中的每个镜头都具有一个类别标签。数据库中具有相同类别标签的镜头与基准点之间的相似度可以转换为它们之间的距离。最后,将查询视频与数据库中视频之间的相似度转换为相似镜头的数量。实验结果表明,该方法可以取得良好的性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号