DocumentCode
3015071
Title
Text detection for video analysis
Author
Agnihotri, Lalitha ; Dimitrova, Nevenka
Author_Institution
Philips Res., Briarcliff Manor, NY, USA
fYear
1999
fDate
1999
Firstpage
109
Lastpage
113
Abstract
Textual information brings important semantic clues in video content analysis. We describe a method for detection and representation of text in video segments. The method consists of seven steps: channel separation, image enhancement, edge detection, edge filtering, character detection, text box detection, and text line detection. Our results show that this method can be applied to English as well as non-English text (such as Korean) with precision and recall of 85%
Keywords
content-based retrieval; edge detection; image enhancement; text analysis; video signal processing; English text; Korean; channel separation; character detection; edge detection; edge filtering; image enhancement; non-English text; semantic clues; text box detection; text detection; text line detection; text representation; textual information; video content analysis; Data mining; Filtering; Image edge detection; Image segmentation; Information retrieval; Layout; Stock markets; Text recognition; Video sequences; Web sites;
fLanguage
English
Publisher
ieee
Conference_Titel
Content-Based Access of Image and Video Libraries, 1999. (CBAIVL '99) Proceedings. IEEE Workshop on
Conference_Location
Fort Collins, CO
Print_ISBN
0-7695-0034-X
Type
conf
DOI
10.1109/IVL.1999.781133
Filename
781133
Link To Document