視訊字幕區域偵測與修復

Video Caption Region Detection and Completion

陳萬鴻(Wan-Hung Chen)

指導教授 ： 郭天穎

國立臺北科技大學/電資學院/電機工程系研究所/碩士(2011年)

摘要

本論文針對視訊內嵌字幕移除提出一個字幕偵測與修補方法。雖然視訊中內嵌的字幕可藉由人工方式以視訊或影像編輯工具抹除掉，但需耗費的龐大精力，因此自動字幕偵測與移除的技術是必須的。目前已有許多自動字幕偵測方法，但並無針對視訊字幕切換(Transition)時的模糊字幕的判斷與偵測提出一套解決辦法，且偵測時易受視訊中複雜背景的影響而造成誤判。
此篇論文中，我們考慮字幕在時間軸的相關性(Temporal Correlation)提出一個視訊字幕切換之判斷與偵測機制，並利用字幕固有的高對比特性來提升字幕偵測的準確度；在字幕移除區域之影像內容修復部分，我們結合影像修補(Image Inpainting)方法與動作向量(Motion Vector)資訊提出一個視訊修補(Video Inpainting)演算法，維持修復結果在空間域與時間域上的一致性與連續性。我們透過實際的廣播節目進行實驗，其結果顯示本論文所提出之字幕偵測與修復方法確實較傳統文獻方法優異。

關鍵字

字幕偵測 ； 字幕切換偵測 ； 影像修補 ； 視訊修補 ； 動作向量

並列摘要

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.

並列關鍵字

Caption Detection ； Caption Transition Detection ； Image Inpainting ； Video Inpainting ； Motion Vector

參考文獻

[1]Wonjun Kim, Changick Kim, “A New Approach for Overlay Text Detection and Extraction From Complex Video Scene,” IEEE Transactions on Image Processing, pp.401-411, 2009.

[2]M. R. Lyu, J. Song and M. Cai, “A comprehensive Method for Multi-lingual Video Text Detection, Localization, and Extraction,” IEEE Trans. on Circuit and Systems for Video Technology, Vol. 15, pp. 243-255, 2005.

[3]Xiaolan Wang, “An Improvement of Chinese Characters Location Algorithm Based on Video,” IEEE Int’l Conf. on Intelligent Information Technology Application, Vol. 2, pp.634, 2008.

[4]T. H. Tsai, Y. C. Chen and C. L. Fang, “A Comprehensive Motion Videotext Detection and Localization and Extraction Method,” IEEE Int’l Conf. on Communications Circuits and Systems, Vol.1, pp.515-519, 2006.

[5]Jing Zhang, D. Goldgof, R. Kasturi, “A New Edge-Based Text Verification Approach for Video,” IEEE Int’l Conf. on Pattern Recognition, pp.1-4, 2008.