| 基于贝叶斯学习的视频检索相关反馈算法设计* |
| |
| 引用本文： | 邓丽,刘小辉,金立左,费树岷.基于贝叶斯学习的视频检索相关反馈算法设计*[J].计算机应用研究,2008,25(3):934-935. |
| |
| 作者姓名： | 邓丽 刘小辉 金立左 费树岷 |
| |
| 作者单位： | 1. 东南大学,自动化研究所,南京,210096
2. 喀什师范学院,计算机科学系,新疆,喀什844001 |
| |
| 基金项目： | 教育部高等学校博士学科点专项科研基金 |
| |
| 摘 要： | 针对信息检索中如何提高检索的精度问题,提出了一个基于相关反馈的视频检索算法.使用概率框架来描述检索问题,并根据贝叶斯学习按照用户的行为来更新概率分布,实现自动相关反馈,提高了检索精度.实验表明,用该算法检索的准确度比基于最近邻特征线(NFL)的视频检索方法有明显提高.
|
| 关 键 词： | 视频检索 相关反馈 贝叶斯学习 |
| 文章编号： | 1001-3695(2008)03-0934-02 |
| 修稿时间： | 2007年2月1日 |
Video retrieval relevance feedback algorithm based on Bayesian learning |
| |
| DENG Li,LIU Xiao hui,JIN Li zuo,FEI Shu min.Video retrieval relevance feedback algorithm based on Bayesian learning[J].Application Research of Computers,2008,25(3):934-935. |
| |
| Authors: | DENG Li LIU Xiao hui JIN Li zuo FEI Shu min |
| |
| Affiliation: | (1. Research Institute of Automation, Southeast University, Nanjing 210096, China; 2. Dept. of Computer Science, Kashi Normal College, Kashi Xinjiang 844001, China) |
| |
| Abstract: | Improving the accuracy of retrieval was very important in information indexing and retrieval. An algorithm of video retrieval based on relevance feedback was presented. It used a probabilistic framework to describe retrieval problem, and updated the probability distribution via Bayesian learning. The results of experiment had been given and compared with the nearest feature line(NFL) based video retrieval. The retrieval precision of this algorithm has better performance. |
| |
| Keywords: | video retrieval relevance feedback Bayesian learning |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用研究》浏览原始摘要信息 |
|
点击此处可从《计算机应用研究》下载全文 |
|
