期刊文献+

基于主色特征识别的新闻视频口播帧 被引量:3

Identification of the Anchorperson Frame in News Video Based on the Dominant Color Features
下载PDF
导出
摘要 基于主色特征识别的新闻视频口播帧是一种全新的口播帧识别方法,该方法首先提取口播帧的主色模板,然后利用该模板对新闻视频的帧序列进行匹配,并由计算机自动对口播帧进行检测和标识。该检测方法与现有的检测方法相比,具有设计简单、计算量小、检测速度快的特点,可以完全做到实时检测。 Based on the dominant color features, a completely new method to identify the anchorperson frames is proposed. At first, the dominant color template is extracted from the anchorperson frames, and then the computer can automatically detect and mark the anchorperson frame through matching the dominant color of every news frame with the template. Compared with other existing methods, this one is very easy to design and can detect completely in a real-time way.
出处 《计算机工程与科学》 CSCD 2004年第8期28-31,共4页 Computer Engineering & Science
基金 重点学科专项基金资助项目(SPKJ016 017)
关键词 模板匹配法 帧图像序列 图像特征 新闻视频口播帧 主色特征识别 news video dominant color anchorperson frame template
  • 相关文献

参考文献7

二级参考文献8

  • 1Saraceno C, Leonardi R. Audio as a Support to Scene Change Detection and Characterization of Video Sequences, In ICASSP-1997, Munich, Germany, 1997-04-21.
  • 2Wang Y, Huang J, Liu Z, et al. Multimedia Content Classification Using Motion and Audio Information. In IEEE International Symposium on Circuit and Systems, Hong Kong, 1997-06:1488-1491.
  • 3Pfeiffer S,Fischer S, Effelsberg W. Automatic Audio Content Analysis.In ACM Multimedia 1996, Boston, MA, 1996-11:18-22.
  • 4Microsoft DirectX 8.0 SDKDocumentation (C++). Microsoft, 2000.
  • 5Huang Q,SPIE 3656,1999年,50页
  • 6Chen L,Proc the 1st IEEE Workshop on Multimedia Signal Processing,1997年,319页
  • 7Swanberg D,IS & T/SPIE San Jose,1993年,13页
  • 8马宇飞,白雪生,徐光祐,史元春.新闻视频中口播帧检测方法的研究[J].软件学报,2001,12(3):377-382. 被引量:24

共引文献25

同被引文献39

  • 1彭培华,曲波,陈荣胜.基于支持向量机的小波域视频字幕检测与提取[J].华南理工大学学报(自然科学版),2004,32(z1):63-66. 被引量:4
  • 2谢毓湘,栾悉道,吴玲达,老松杨.新闻视频帧中的字幕探测[J].计算机工程,2004,30(20):167-168. 被引量:15
  • 3李默,李弼程,邓子健.新闻视频主持人镜头的半屏幕检测算法[J].计算机工程与应用,2005,41(15):183-185. 被引量:4
  • 4ChenghuaX YunhongW TieniuT etal.Face recognition using 3D eigenfaces[A]..生物识别研究新进展(2)[C].北京:清华大学出版社,2003.3-10.
  • 5Gunsel B, Ferman A M. Video Indexing Through Integration of Syntactic and Semantic Features[C]//Proc. of the 3rd Workshop on Application of Computer Vision. Sarasota, Florida: [s. n.], 1996: 90-95.
  • 6Yang Jun, Hauptmann A. Multi-modality Analysis for Person Type Classification in News Video[C]//Proc. of SPIE in Media Computing and Networking. San Jose: [s. n.], 2005: 165-172.
  • 7Shearer K, Dorai C, Venkatash S. Incorporating Domain Knowledge with Video and Voice Data Analysis in News Broadcasts[C]//Proc. of the 1st International Workshop on Multimedia Data Mining. Boston, MA, USA: [s. n.], 2000-08: 46-53.
  • 8Lienhart R, Pfeiffer S, Effelsberg W. Video Abstracting[J]. Communications of the ACM. 1997, 40(12): 55-62.
  • 9Galton S E Personal identification and description-Ⅰ[J]. Nature ,1888,21:173 - 177.
  • 10Wang J G, Tam T N. A new face detection method based on shape information[J]. Pattern Recognition Letters,2000,21 (6/7) : 463 - 471.

引证文献3

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部