Video Text Extraction Based on Stroke Width and Color

DOI

10.2991/icmt-13.2013.77How to use a DOI?

Keywords

Text extraction, K-means, High-frequency Emphasis, Text Stroke Width

Abstract

Video text can be used to infer important semantics information of video. Video text extraction is a crucial step to recognize video text. Most of previous works can not extract the text well when the text regions have complex background or text character stroke width is unknown. Therefore, we propose a text extraction method, which can accurately extract the video text in complex background and various text character sizes. Experimental results on TV news video show the encouraging performance of the proposed algorithm.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Huang Xiaodong
AU  - Wang Qin
AU  - Liu Kehua
AU  - Zhu Lishang
PY  - 2013/11
DA  - 2013/11
TI  - Video Text Extraction Based on Stroke Width and Color
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 622
EP  - 629
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.77
DO  - 10.2991/icmt-13.2013.77
ID  - Xiaodong2013/11
ER  -