Key frame extraction for text based video retrieval using Maximally Stable Extremal Regions

© 2015 ICST. 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 (MSE...

Full description

Saved in:
Bibliographic Details
Main Authors: Werachard Wattanarachothai, Karn Patanukhom
Format: Conference Proceeding
Published: 2018
Subjects:
Online Access:https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84943327896&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/44422
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
id th-cmuir.6653943832-44422
record_format dspace
spelling th-cmuir.6653943832-444222018-04-25T07:51:17Z Key frame extraction for text based video retrieval using Maximally Stable Extremal Regions Werachard Wattanarachothai Karn Patanukhom Agricultural and Biological Sciences © 2015 ICST. 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. 2018-01-24T04:42:37Z 2018-01-24T04:42:37Z 2015-01-01 Conference Proceeding 2-s2.0-84943327896 10.4108/icst.iniscom.2015.258410 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84943327896&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/44422
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
topic Agricultural and Biological Sciences
spellingShingle Agricultural and Biological Sciences
Werachard Wattanarachothai
Karn Patanukhom
Key frame extraction for text based video retrieval using Maximally Stable Extremal Regions
description © 2015 ICST. 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.
format Conference Proceeding
author Werachard Wattanarachothai
Karn Patanukhom
author_facet Werachard Wattanarachothai
Karn Patanukhom
author_sort Werachard Wattanarachothai
title Key frame extraction for text based video retrieval using Maximally Stable Extremal Regions
title_short Key frame extraction for text based video retrieval using Maximally Stable Extremal Regions
title_full Key frame extraction for text based video retrieval using Maximally Stable Extremal Regions
title_fullStr Key frame extraction for text based video retrieval using Maximally Stable Extremal Regions
title_full_unstemmed Key frame extraction for text based video retrieval using Maximally Stable Extremal Regions
title_sort key frame extraction for text based video retrieval using maximally stable extremal regions
publishDate 2018
url https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84943327896&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/44422
_version_ 1681422556549087232