DocumentCode :
3154790
Title :
A robust system for text extraction in video
Author :
Zhou, Jingchao ; Xu, Lei ; Xiao, Baihua ; Dai, Ruwei ; Si, Si
Author_Institution :
Chinese Acad. of Sci., Beijing
fYear :
2007
fDate :
28-29 Dec. 2007
Firstpage :
119
Lastpage :
124
Abstract :
This paper presents a novel system to extract caption text in video. Firstly, text regions are detected primarily with emphasis on the recall rate. Then a multiple stage verification scheme is adopted to discard false alarms and boost the precision rate. Secondly, a text polarity estimation algorithm is provided. Based on it, multiple frame enhancement is conducted to strengthen the contrast between text and its background. Finally, a connected component filtering method is proposed to generate clear segmentation results and improve recognition performance. Experimental results confirm that the proposed system is robust and efficient.
Keywords :
image segmentation; text analysis; video signal processing; clear segmentation; connected component filtering method; multiple frame enhancement; multiple stage verification; robust system; text polarity estimation algorithm; video text extraction; Automation; Content based retrieval; Data mining; Filtering; Gabor filters; Image color analysis; Image generation; Image segmentation; Information retrieval; Robustness; multiple frame enhancement; polarity estimation; text detection; text extraction; video information retrieval;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Vision, 2007. ICMV 2007. International Conference on
Conference_Location :
Islamabad
Print_ISBN :
978-1-4244-1624-0
Electronic_ISBN :
978-1-4244-1625-7
Type :
conf
DOI :
10.1109/ICMV.2007.4469284
Filename :
4469284
Link To Document :
بازگشت