A study of detecting and reconstructing marquee texts in natural scenes
碩士 === 國立中央大學 === 資訊工程研究所 === 100 === Many devices such as advertisements, TV wall, traffic signals and marquee (scrolling text) are delivering multimedia contents in our daily lives. People may miss some important information when facing so many different multimedia contents. This thesis proposes a...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2012
|
Online Access: | http://ndltd.ncl.edu.tw/handle/01090417017906270545 |
id |
ndltd-TW-100NCU05392131 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-100NCU053921312015-10-13T21:22:39Z http://ndltd.ncl.edu.tw/handle/01090417017906270545 A study of detecting and reconstructing marquee texts in natural scenes 自然場景跑馬燈偵測與完整文句重構 Hou-An Chen 陳厚安 碩士 國立中央大學 資訊工程研究所 100 Many devices such as advertisements, TV wall, traffic signals and marquee (scrolling text) are delivering multimedia contents in our daily lives. People may miss some important information when facing so many different multimedia contents. This thesis proposes a vision-based approach to assist users avoiding missing information that might be important to them. This study aims the marquee the messages it contains are constantly updating so that people miss part of the contents easily. The purpose of work is to display the full contents shown by a marquee. First, the system locates the marquee texts by analyzing the optical flow field. Meanwhile, the starting and ending time of scrolling texts can also be obtained. Second, text blocks are retrieved by the integration of temporal differencing, vertical projection, and histogram matching method. Finally, the content of the marquee is displayed by rearranging these text blocks. Experiments demonstrate that the proposed method can display most texts in the marquee regardless of the language or color of texts. Kuo-Chin Fan 范國清 2012 學位論文 ; thesis 57 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中央大學 === 資訊工程研究所 === 100 === Many devices such as advertisements, TV wall, traffic signals and marquee (scrolling text) are delivering multimedia contents in our daily lives. People may miss some important information when facing so many different multimedia contents. This thesis proposes a vision-based approach to assist users avoiding missing information that might be important to them. This study aims the marquee the messages it contains are constantly updating so that people miss part of the contents easily. The purpose of work is to display the full contents shown by a marquee.
First, the system locates the marquee texts by analyzing the optical flow field. Meanwhile, the starting and ending time of scrolling texts can also be obtained. Second, text blocks are retrieved by the integration of temporal differencing, vertical projection, and histogram matching method. Finally, the content of the marquee is displayed by rearranging these text blocks. Experiments demonstrate that the proposed method can display most texts in the marquee regardless of the language or color of texts.
|
author2 |
Kuo-Chin Fan |
author_facet |
Kuo-Chin Fan Hou-An Chen 陳厚安 |
author |
Hou-An Chen 陳厚安 |
spellingShingle |
Hou-An Chen 陳厚安 A study of detecting and reconstructing marquee texts in natural scenes |
author_sort |
Hou-An Chen |
title |
A study of detecting and reconstructing marquee texts in natural scenes |
title_short |
A study of detecting and reconstructing marquee texts in natural scenes |
title_full |
A study of detecting and reconstructing marquee texts in natural scenes |
title_fullStr |
A study of detecting and reconstructing marquee texts in natural scenes |
title_full_unstemmed |
A study of detecting and reconstructing marquee texts in natural scenes |
title_sort |
study of detecting and reconstructing marquee texts in natural scenes |
publishDate |
2012 |
url |
http://ndltd.ncl.edu.tw/handle/01090417017906270545 |
work_keys_str_mv |
AT houanchen astudyofdetectingandreconstructingmarqueetextsinnaturalscenes AT chénhòuān astudyofdetectingandreconstructingmarqueetextsinnaturalscenes AT houanchen zìránchǎngjǐngpǎomǎdēngzhēncèyǔwánzhěngwénjùzhònggòu AT chénhòuān zìránchǎngjǐngpǎomǎdēngzhēncèyǔwánzhěngwénjùzhònggòu AT houanchen studyofdetectingandreconstructingmarqueetextsinnaturalscenes AT chénhòuān studyofdetectingandreconstructingmarqueetextsinnaturalscenes |
_version_ |
1718061610447142912 |