DocumentCode :
507332
Title :
A Novel Approach for Captions Detection in Video Sequences
Author :
Wang, Xingqi ; Dong, Guang
Author_Institution :
Sch. of Comput. Sci., Hangzhou Dianzi Univ., Hangzhou, China
Volume :
5
fYear :
2009
fDate :
14-16 Aug. 2009
Firstpage :
325
Lastpage :
329
Abstract :
Text detection for video sequences has played an important role in real world applications. In the paper, new text detectors based on text intrinsic structures were proposed. Temporal information was employed to remove false positive features. And density-based method was introduced as post-processing step to filter out noises. Experimental results show that proposed approach could obtain challenging results with higher precision and recall rate.
Keywords :
character recognition; video signal processing; captions detection; false positive features; temporal information; text detection; text intrinsic structures; video sequences; Computer science; Computer vision; Data mining; Detectors; Filters; Fuzzy systems; Hysteresis; Image edge detection; Text recognition; Video sequences; clustering; temporal information; text detection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Systems and Knowledge Discovery, 2009. FSKD '09. Sixth International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-0-7695-3735-1
Type :
conf
DOI :
10.1109/FSKD.2009.334
Filename :
5360607
Link To Document :
بازگشت