Overlay Text Detection in Complex Video Background

NCUTIR > College of Electrical Engineering and Computer Science > Department of Computer Science and Information Engineering > The 5th Imtelligent Living Technology Conference > Item 987654321/3499

Please use this identifier to cite or link to this item: http://ir.lib.ncut.edu.tw/handle/987654321/3499

Title:	Overlay Text Detection in Complex Video Background
Authors:	Chun-Cheng Lin Bo-Min Yen
Contributors:	Department of Electrical Engineering National Chin-Yi University of Technology
Keywords:	Transition map Overlay text detection Video subtitles Local binary pattern Texture analysis
Date:	2010-06
Issue Date:	2010-09-15 09:46:56 (UTC+8)
Abstract:	The subtitles on video are very useful for us to understand video's contents. If we can extract text information from the subtitles, it will be very helpful to establish a database of video’s content that includes annotations and indexes. To extract text from videos, most text detection and extraction methods use the text color, background contrast, and texture information. However, the limitations of the existing methods are various contrasts and complex backgrounds in the text processing. The purpose of this study is to develop a method to detect overlay text in the complex video background. This study utilized the characteristics that there are transient color changes existing between text and its adjacent background, to generate transition maps. And this work applied the connected components to smooth the connected rectangular shapes. The study results demonstrated that the text detection method based on the transition map can effectively detect the text regions under different text contrasts, fonts and background complexities.
Relation:	第五屆智慧生活科技研討會論文集(上)
Appears in Collections:	[Department of Computer Science and Information Engineering] The 5th Imtelligent Living Technology Conference

Files in This Item:

File	Description	Size	Format
Overlay Text Detection in Complex Video Background.pdf		145Kb	Adobe PDF	3382	View/Open

Loading...