|Table of Contents|

TV Symbol Recognition Based on Weighted Hu Invariant Moments in HSV Colour Space

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2005年03期
Page:
363-367
Research Field:
Publishing date:

Info

Title:
TV Symbol Recognition Based on Weighted Hu Invariant Moments in HSV Colour Space
Author(s):
ZHOU Xian-zhong1 SHI Ying-chun 23 WANG Tao2
1. School of Engineering and Management, Nanjng University , Nanjing 210093, China; 2. Department of Automation, NUST, Nanjing 210094, China; 3. Simulation Center, Wuhan Institute of Communication Command, Wuhan 430010, China
Keywords:
video retrieval TV station symbo l recognition w e ightedHu invariantmoments spatio-temporal invariant
PACS:
TP391.41
DOI:
-
Abstract:
A cco rd ing to the v isua l features of aTV station symbo,l TV station symbo l is segmented by the detection o f spat io-tempo ral invariant reg ion. The fea tures of a TV station symbol are described w ith w e ightedHu invariant moments inHSV co lo r space and recognized on the basis o f know ledge base. The algorithm is experim enta lly satisfy ing

References:

[ 1] Yeo B L, YeungM M. Retrieving and v isualizing v ideo [ J]. ACM Communication. 1997, 40( 12): 47- 52.
[ 2] Chang S F, ChenW, Sundaram H. V ideoQ: An automated content based video search system using visua l cues [ A]. Seattle: ACM Mu ltmi edia 1997, 1997: 313- 324.
[ 3 ] W actlar H, Kanade T, Sm ith M. Inte lligent access to dig ital v ideo: inform ed ia pro ject [ J]. IEEE Compu ter, 1999, 29( 6): 46- 52.
[ 4] 詹国华, 庄越挺, 吴羿. 基于全局与局部特征的视频索引模型[ J]. 计算机辅助设计与图形学学报, 2000, 12 ( 12): 911- 916.
[ 5] Chan SM, LiQ, Wu Y. Accommodation hybrid re trieval in a comprehensive video database managem ent system [ J]. IEEE Traction on mu ltmi ed ia, 2002, 4( 2): 146- 159.
 [ 6] 张越挺, 刘骏伟, 吴飞. 基于支持向量机的视频字幕自动定位与提取[ J]. 计算机辅助设计于图形学学报, 2002, 14( 8) : 750- 753.
[ 7] 吴飞, 庄越挺, 郑科, 等. 基于压缩域特征话者识别的电视节目分类检索[ J]. 模式识别域人工智能, 2002, 15( 1) : 21- 26.
[ 8] 季白杨, 陈纯, 钱英. 视频分割技术的发展[ J]. 计算机研究与发展, 2001, 38( 1): 36- 42.
[ 9] A. Nurat Tekalp. 数字视频处理[M ]. 崔之祐, 江春, 陈丽鑫译. 北京: 电子工业出版社, 1998.
[ 10] 章毓晋. 图像理解与计算机视觉[M ]. 北京: 清华大学出版社, 2000.
[ 11] 章毓晋. 图像处理和分析[M ]. 北京: 清华大学出版社, 1999.
[ 12] John P, Boardman JM, Graham M E. Shape-based retr ieva:l A case study w ith tradem ark im age databases [ J]. Pattern Recogn ition, l998, 3l( 9): 1 360- 1 390.
[ 13] Garg i U, O swa ld S, Kosiba D. Eva luation of v ideo sequence index ing and k ierarch ica l v ideo index ing [ A ]. Storag e Retriva l Image V ideo Da tabase [ C ]. [ S. L. ]: SPIE, 1995, 2420. 144- 151.
[ 14] H a tam ianM. A rea-l tim e two-d imensional mom ent gene rating a lgo rithm and its sing le chip im plem entation [ J]. IEEE T rans: Acoustics, Speech, and S ignal Processing, 1986, 34( 3) : 546- 553.

Memo

Memo:
-
Last Update: 2013-03-03