About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
el 15(7): e5

Research Article

Key Frame Extraction for Text Based Video Retrieval Using Maximally Stable Extremal Regions

Download1325 downloads
Cite
BibTeX Plain Text
  • @ARTICLE{10.4108/icst.iniscom.2015.258410,
        author={Werachard Wattanarachothai and Karn Patanukhom},
        title={Key Frame Extraction for Text Based Video Retrieval Using Maximally Stable Extremal Regions},
        journal={EAI Endorsed Transactions on e-Learning},
        volume={2},
        number={7},
        publisher={EAI},
        journal_a={EL},
        year={2015},
        month={4},
        keywords={cbvr, text-based video retrieval, key frame extraction, shot boundary, mser},
        doi={10.4108/icst.iniscom.2015.258410}
    }
    
  • Werachard Wattanarachothai
    Karn Patanukhom
    Year: 2015
    Key Frame Extraction for Text Based Video Retrieval Using Maximally Stable Extremal Regions
    EL
    EAI
    DOI: 10.4108/icst.iniscom.2015.258410
Werachard Wattanarachothai1, Karn Patanukhom1,*
  • 1: Chiang Mai University
*Contact email: karn@eng.cmu.ac.th

Abstract

This paper presents a new approach for text-based video content retrieval system. The proposed scheme consists of three main processes that are key frame extraction, text localization and keyword matching. For the key-frame extraction, we proposed a Maximally Stable Extremal Region (MSER) based feature which is oriented to segment shots of the video with different text contents. In text localization process, in order to form the text lines, the MSERs in each key frame are clustered based on their similarity in position, size, color, and stroke width. Then, Tesseract OCR engine is used for recognizing the text regions. In this work, to improve the recognition results, we input four images obtained from different pre-processing methods to Tesseract engine. Finally, the target keyword for querying is matched with OCR results based on an approximate string search scheme. The experiment shows that, by using the MSER feature, the videos can be segmented by using efficient number of shots and provide the better precision and recall in comparison with a sum of absolute difference and edge based method.

Keywords
cbvr, text-based video retrieval, key frame extraction, shot boundary, mser
Published
2015-04-09
Publisher
EAI
http://dx.doi.org/10.4108/icst.iniscom.2015.258410

Copyright © 2015 W. Wattanarachothai and K. Patanukhom, licensed to EAI. This is an open access article distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/3.0/), which permits unlimited use, distribution and reproduction in any medium so long as the original work is properly cited.

EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL