Automatic Video Scene Segmentation to Separate Script for OCR

Abstract

In Text or character recognition in images or video frames is a difficult problem to achieve video data. This paper proposes improved template matching algorithm that applied for the automatic extraction of text from image and video frames. Optical character recognition using template matching is a system model that is useful to recognize the character, digits& special character by comparing two images of the alphabet. The objectives of this system model are to develop a model for the Optical Character Recognition (OCR) system and to implement the template matching algorithm in developing the system model . The template matching techniques are more profound to font and size variations of the characters than the feature classification methods. This system tested the 35 videos with 700 video frames for each video. Empirical result of this system precision rate is 91. 52% for automatic character gets recognized images and video frames. Experimental results show the relatively high accuracy of the new developed robust algorithm when it is tested on several size characters and text.

References

• Xian-Sheng Hua, Liu Wenyin, Hong-Jiang Zhang. 2001," Automatic Performance Evaluation for Video Text Detection," Sixth InternationalConference on Document Analysis and Recognition (ICDAR2001), pp 545-550, Seattle, Washington, U. S. A. , September 10-13, (2001).
• KeechulJunga, Kwang In Kimb, Anil K. Jain. 2003"Text information extraction in images and video: a survey,"Published by Elsevier Ltd. (2003).
• Canny, J. 1986, "A Computational Approach to Edge Detection,"IEEE Trans. Pattern Analysis and Machine Intelligence, 8:679-714, November (1986).
• H. K. Kim, ECcien. 1996," automatic text location methodand content-based indexing and structuring of video database,"J. Visual Commun. Image Representation 7 (4) 336–344(1996).
• Y. Zhong, A. K. Jain. 2000," Object localization using color, texture, andshape," Pattern Recognition 33 671–684(2000).
• S. Antani, R. Kasturi, R. Jain. 2002," A survey on the use of pattern recognition methods for abstraction, indexing, and retrieval ofImages andvideo, "Pattern Recognition 35 945–965(2002).
• Xi Jie, Xian-Sheng Hua, Xiang-Rong Chen, Liu Wenyin, HongJiang Zhang. 2009" A Video Text Detection and Recognition System, "IEEE International( 2009).
• P. Shivakumara, W. Huang and C. L. Tan. 2008: Efficient Video Text Detection Using Edge Features, The Eighth IAPR Workshop on Document Analysis Systems (DAS2008), Nara, Japan, pp 307-314(2008).
• Rainer Lienhart and Frank Stuber,"Automatic text recognition in digital videos," University of Mannheim, PraktischeInformatik IV, 68131 Mannheim, Germany.
• Qixiang Ye, W. Gao, W. Wang and W. Zeng. 2003,"A Robust Text Detection Algorithm in Images and Video Frames," IEEE ICICS-PCM, pp. 802-806, (2003).
• G. Aghajari, J. Shanbehzadeh, and A. Sarrafzadeh. 2010," A Text Localization Algorithm in Color Image via New Projection Profile,"IMECS Hong Kong (2010).
• JayshreeGhorpade, Raviraj Palvankar. 2011,"Extracting Text From Video," Signal & Image Processing , An International Journal (SIPIJ) Vol. 2, No. 2, (2011).
• Bharatratna GaikwadRamesh R. Manza. 2011," Critical review on video scene segmentation and Recognition ," International Journal of Computer Information Systems (IJCIS), Vol 3, and Number 3, (2011).
• Ramesh R. Manza and Bharatratna P. Gaikwad. 2012,"A Video Edge Detection Using Adaptive Edge Detection Operator," Issue: January 2012, DOI: DIP012012006, CiiT International Journal of Digital Image Processing: ISSN: 0974–9691 & Online: ISSN: 0974-9586.
• Manza R. R. , GaikwadB. P. , Manza G. R. 2012,"Use Of Edge Detection Operators For Agriculture Video Scene Feature Ex-Traction From Mango Fruits," Advances in Computational Research, ISSN: 0975-3273 & E-ISSN: 0975-9085, Vol 4, Issue 1, 2012, pp. -50-53.
• Manza Ramesh R. , Bharatratna P. Gaikwad, Manza Ganesh R. 2012,"Used of Various Edge Detection Operators for Feature Extraction in Video Scene," ICACEEE-Jan-2012Proc. of the Intl. Conf. on Advances in Computer, Electronics and Electrical Engineering ,ISBN: 978-981-07-1847-3(2012).
• C. P. Sumathi,T. Santhanam, N. Priya. 2012 ,"Techniques and challenges of automatic text extraction in complex images: a survey", Journal of Theoretical and Applied Information Technology, 31st January 2012. Vol. 35 No. 2
• Keechul Jung, Kwang In Kim, Anil K. Jain. 2004,"Text Information Extraction in Images and Video: A Survey ",the journal of the Pattern Recognition society, 2004.
• SnehaSharma. 2006,"Extraction of Text Regions in Natural Images",Masters Project Report, Spring 2006/07.
• AyatullahFarukMollah,,NabamitaMajumder. 2011, "Design of an Optical Character Recognition System for Camerabased Handheld Devices ",IJCSI ,Issues, Vol. 8, Issue 4, No 1, July 2011.
• Yih-Ming Su, Chaur-Heh Hsieh. 2006, "A Novel Model-Based Segmentation Approach To Extract Caption Contents On Sports Videos", IEEE International Conference On Multimedia And Expo,pp:1829 - 1832 .
• Miriam Leon, Veronica Vilaplana, AntoniGasull, Ferran Marques. 2009 , "Caption Text Extraction For Indexing Purposes Using A Hierarchical Region-Based Image Model",Proceedings Of The 16th IEEE International Conference On Image Processing, pp:1869-1872.
• u Zhong, Hongjiang Zhang, And Anil K. Jain. 1999,"Automatic Caption Localization InCompressed Video", International Conference On Image Processing, pp: 96 - 100 Vol. 2.
• XiaoqianLiu,Weiqiang Wang. 2010 ,"Extracting Captions From Videos Using TemporalFeature",Proceedings Of The International Conference On Acm Multimedia ,pp:843-846.
• Bo Lilo, Xaoou Tang, Jianzhuang Liu, And Hongiiang Zhan. 2003 ,"Video Caption Detection And Extraction Using Temporal Information", International Conference On Image Processing, Vol. 1 , pp:I 297-300
• Bharatratna P. Gaikwad , Ramesh R. Manza,Manza R. Ganesh. 2013 , "Video scene segmentation to separate script", Advance Computing Conference (IACC), 2013 IEEE xploreieee , 978-1-4673-4527-9.

Index Terms

Keywords