Video Caption Region Detection and Completion
碩士 === 國立臺北科技大學 === 電機工程系研究所 === 99 === This paper proposed a video text detection and completion method to remove embedded captions in broadcasting programs. One may remove captions manually frame by frame using image editing tools, but it takes a considerable amount of time and efforts. Many a...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2011
|
Online Access: | http://ndltd.ncl.edu.tw/handle/7p7444 |
id |
ndltd-TW-099TIT05442078 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-099TIT054420782019-05-15T20:42:28Z http://ndltd.ncl.edu.tw/handle/7p7444 Video Caption Region Detection and Completion 視訊字幕區域偵測與修復 Wan-Hung Chen 陳萬鴻 碩士 國立臺北科技大學 電機工程系研究所 99 This paper proposed a video text detection and completion method to remove embedded captions in broadcasting programs. One may remove captions manually frame by frame using image editing tools, but it takes a considerable amount of time and efforts. Many automatic text detection methods have been proposed to solve this problem, but none of existing methods considered real scenarios where captions suffer from caption transition and complicated background. This work develops a real time caption detection algorithm by making use of the temporal relation observed in caption transition, and improves the caption detection rate in complicated background using high contrast property found in spatial domain. To complete the detected caption region, we extend an exemplar-based image inpainting algorithm by incorporating motion vectors to the completion priority for video inpainting, so as to maintain spatial consistency and temporal continuity in playback. Experiments are performed on real television broadcast video clips, and shows that the proposed text detection and completion method is superior to other methods. 郭天穎 2011 學位論文 ; thesis 69 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺北科技大學 === 電機工程系研究所 === 99 === This paper proposed a video text detection and completion method to remove embedded captions in broadcasting programs. One may remove captions manually frame by frame using image editing tools, but it takes a considerable amount of time and efforts. Many automatic text detection methods have been proposed to solve this problem, but none of existing methods considered real scenarios where captions suffer from caption transition and complicated background. This work develops a real time caption detection algorithm by making use of the temporal relation observed in caption transition, and improves the caption detection rate in complicated background using high contrast property found in spatial domain. To complete the detected caption region, we extend an exemplar-based image inpainting algorithm by incorporating motion vectors to the completion priority for video inpainting, so as to maintain spatial consistency and temporal continuity in playback. Experiments are performed on real television broadcast video clips, and shows that the proposed text detection and completion method is superior to other methods.
|
author2 |
郭天穎 |
author_facet |
郭天穎 Wan-Hung Chen 陳萬鴻 |
author |
Wan-Hung Chen 陳萬鴻 |
spellingShingle |
Wan-Hung Chen 陳萬鴻 Video Caption Region Detection and Completion |
author_sort |
Wan-Hung Chen |
title |
Video Caption Region Detection and Completion |
title_short |
Video Caption Region Detection and Completion |
title_full |
Video Caption Region Detection and Completion |
title_fullStr |
Video Caption Region Detection and Completion |
title_full_unstemmed |
Video Caption Region Detection and Completion |
title_sort |
video caption region detection and completion |
publishDate |
2011 |
url |
http://ndltd.ncl.edu.tw/handle/7p7444 |
work_keys_str_mv |
AT wanhungchen videocaptionregiondetectionandcompletion AT chénwànhóng videocaptionregiondetectionandcompletion AT wanhungchen shìxùnzìmùqūyùzhēncèyǔxiūfù AT chénwànhóng shìxùnzìmùqūyùzhēncèyǔxiūfù |
_version_ |
1719103657605070848 |