Style-sheets Extraction from Existing Digital Contents by Image Processing for Web-Based BML Contents Management System

This paper proposes a web-based BML contentsmanagement system. BML is the short form of BroadcastMarkup Language which is a script language for databroadcasting contents included in digital TV broadcastingservices of Japan. The scripting style of BML is very similar tothat of HTML and it also supports style-sheets and JavaScript.However, in BML, there are many restrictions about thedisplay area size, font sizes, color types and so on because theBML-browser of TV is not flexible as compared with the Webbrowser.Although there are a couple of dedicated softwarepackages for BML contents creation, they are very expensiveand difficult to use. So, BML contents creation is not easy forthe end-user. To make it easier to create BML contents, theauthors have been developing a webbased BML contentsmanagement system. This paper explains fundamentalfunctionalities provided by the proposed BML contentsmanagement system.Already many digital contents were created and stored andwe can easily obtain their images by capturing the screensnapshot. So, this paper also proposes style-sheets extractionmethod for BML contents from such already existing digitalcontents by image processing techniques.

[1]  Qian Huang,et al.  Automated generation of news content hierarchy by integrating audio, video, and text information , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[2]  G. Nocent,et al.  Imagine: a tool for generating HTML style sheets with an interactive genetic algorithm based on genes frequencies , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[3]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  David H. Douglas,et al.  ALGORITHMS FOR THE REDUCTION OF THE NUMBER OF POINTS REQUIRED TO REPRESENT A DIGITIZED LINE OR ITS CARICATURE , 1973 .

[5]  Nobuo Ezaki,et al.  Text detection from natural scene images: towards a system for visually impaired persons , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[6]  Thomas M. Breuel,et al.  The OCRopus open source OCR system , 2008, Electronic Imaging.

[7]  Nobuo Ezaki,et al.  Text reading system based on extraction of a character in camera image for visually impaired person , 2006 .

[8]  Chitra Dorai,et al.  Automatic text extraction from video for content-based annotation and retrieval , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).