臺灣博碩士論文加值系統

在這篇論文裡，一個利用新聞影片為題材的網頁式英文學習系統被提出。我們相信新聞主播或記者的聲音以及新聞影片的文字可以幫助非英文語系的使用者學習英文。為了對學習的題材做加值，我們選擇使用英語播報以及提供英文字幕的新聞影片。一般來說，當影片的聲音以及文字是使用同一種語言，則影片的字幕通常稱之為“closed-captions”。為了促進新聞字幕的實用性，我們使用影片文字抽取技術來萃取新聞影片的字幕以及對字幕的單字做範圍的標定。萃取出來的字幕可以提供跨媒體的存取，而字幕單字範圍的標定有助於我們提供使用者做單字的查詢。我們從新聞影片中萃取出來的字幕資訊幫助我們實現一個實用而且可以改善學習者的聽力與閱讀能力的應用程式。

In this thesis, a Web-based English learning system using news video materials has been proposed. We believe that the anchorperson’ or reporters’ speech and text of news video are helpful for non-native users to learn English. In order to add more value of the learning materials, we choose the news video which was reported with video text in English. Generally, when both speech and video text are in the same language, the video text is usually called “closed-captions”. To facilitate the accessibility of the closed-captions, we use video text extraction technique to extract the closed-captions and to locate the position of words. The extracted closed-captions provide important clues for cross-media access, and the located words benefit the looking up vocabulary in an online dictionary. The information we discovered from the news video helps us to design a feasible application that helps learners to improve their listening and reading abilities.

Contents I
List of Figures III
List of Tables IV
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Introduction 1
1.3 Research Issues 2
1.4 Organization of this Thesis 3
Chapter 2 Related Works 4
2.1 Computer-Assisted Language Learning (CALL) System 4
2.2 Optical Character Recognition (OCR) 4
2.3 Video Text Extraction 5
Chapter 3 System Architecture 7
Chapter 4 News Video Closed-Captions Extraction 10
4.1 Closed-Captions Tracking 10
4.2 Closed-Captions Extraction 12
4.2.1 Edge Detection 12
4.2.2 Smoothing Processing 13
4.2.3 Text Box Projection 15
4.2.4 Text Box Verification 15
4.2.5 Text Box Binarization 16
4.2.6 Optical Character Recognition (OCR) Engine 17
4.3 Closed-Captions Correcting Mechanism 17
Chapter 5 Word Position Determination 20
5.1 Word Position Determination 20
5.1.1 The Morphological Operator 21
5.2 The Video Text Corresponding Position Binding 22
Chapter 6 System Framework and Implementation 25
6.1 System Framework 25
6.2 Implementation 26
6.2.1 Asynchronous JavaScript and XML (AJAX) 26
6.3 User Interface 28
Chapter 7 Experimental Results 32
7.1 The Evaluation of the Word Position Determination 32
7.2 The Evaluation of Online Dictionary Assistant 33
Chapter 8 Conclusion and Future Work 35
8.1 Conclusion 35
8.2 Future Work 35
References 36
Internet References 37

[1] Jason A. Brotherton, and Gregory D. Abowd "Lessons learned from eClass: Assessing automated capture and access in the classroom." ACM Transactions on Computer-Human Interaction, 11, 2 (June 2004), 121-155.
[2] Herng-Yow Chen, Gin-Yi Chen, and Jen-Shin Hong "Design of a Web-based Synchronized Multimedia Lecture System for Distance Education." In Proceedings of the IEEE International Conference on Multimedia Computing and Systems (Florence, Italy, June 07-11), 1999, 887-891.
[3] Chong-Wah Ngo, and Chi-Kwong Chan,, "Video text detection and segmentation for optical character recognition", Multimedia Systems,.pp. 117-120, March 2005
[4] Christine Canning-Wilson, "Practical Aspects of Using Video in the Foreign Language Classroom", The Internet Teachers of English as a Second Language (TESL) Journal, available on http://iteslj.org/Articles/Canning-Video.html, Nov. 2000
[5] Jie Xi, Xian-Sheng Hua, Xiang-Rong Chen, Liu Wenyin, and Hong-Jiang Zhang, "A video text detection and recognition system", IEEE Int. Conference on Multimedia and Expo (ICME2001), pp. 873-876, Aug. 2001
[6] M. Cai, J. Song, and M.R. Lyu, "A new approach for video text detection", IEEE Int. Conference on Image Processing, pp. 117-120, Sept. 2002
[7] Muller, R., and Ottmann, T. "The "Authoring on the Fly" system for automated recording and replay of (tele)presentations." Multimedia Systems, pp. 158-176, Oct. 2000
[8] Qixiang Ye, Wen Gao, Weiqiang Wang, and Wei Zeng, "A robust text detection algorithm in images and video frames", Communications and Signal Processing, pp.802-806, Dec. 2003
[9] Sheng-Wei Li, Hao-Tung Lin, and Herng-Yow Chen, "How Speech/Text Alignment Benefits Web-based Learning", ACM Press, Proceedings of the 13th annual ACM international conference on Multimedia, Singapore, pp. 259-260, 2005
[10] X.S. Hua, P. Yin, and H.J. Zhang, "Efficient video text recognition using multiple frame integration", IEEE Int. Conference on Image Processing, pp.379-400, Sept. 2002
[11] Yong, Zhao, "Language Learning on the World Wide Web: Toward a Framework of Network based CALL", Journal of Computer Assisted Language Instruction Consortium, Vol. 14, No. 1, 1996.