Cover Image

High level semantic concept retrieval using a hybrid similarity method

In video search and retrieval, user’s need is expressed in terms of query. Early video retrieval systems usually matched video clips with such low-level features as color, shape, texture, and motion. In spite of the fact that retrieval is done accurately and automatically with such low-level feature...

Full description

Saved in:
Bibliographic Details
Main Authors: Kouchehbagh, Sara Memar, Affendey, Lilly Suriani, Mustapha, Norwati, C. Doraisamy, Shyamala, Ektefa, Mohammadreza
Other Authors: Lukose, Dickson
Format: Book Section
Published: Springer 2012
Online Access:http://psasir.upm.edu.my/id/eprint/26091/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.26091
record_format eprints
spelling my.upm.eprints.260912016-01-19T04:29:40Z http://psasir.upm.edu.my/id/eprint/26091/ High level semantic concept retrieval using a hybrid similarity method Kouchehbagh, Sara Memar Affendey, Lilly Suriani Mustapha, Norwati C. Doraisamy, Shyamala Ektefa, Mohammadreza In video search and retrieval, user’s need is expressed in terms of query. Early video retrieval systems usually matched video clips with such low-level features as color, shape, texture, and motion. In spite of the fact that retrieval is done accurately and automatically with such low-level features, the semantic meaning of the query cannot be expressed in this way. Moreover, the limitation of retrieval using desirable concept detectors is providing annotations for each concept. However, providing annotation for every concept in real world is very challenging and time consuming, and it is not possible to provide annotation for every concept in the real world. In this study, in order to improve the effectiveness of the retrieval, a method for similarity computation is proposed and experimented for mapping concepts whose annotations are not available onto the annotated and known concepts. The TRECVID 2005 data set is used to evaluate the effectiveness of the concept-based video retrieval model by applying the proposed similarity method. Results are also compared with previous similarity measures used in the same domain. The proposed similarity measure approach outperforms other methods with the Mean Average Precision (MAP) of 26.84% in concept retrieval. Springer Lukose, Dickson Ahmad, Abdul Rahim Suliman, Azizah 2012 Book Section PeerReviewed Kouchehbagh, Sara Memar and Affendey, Lilly Suriani and Mustapha, Norwati and C. Doraisamy, Shyamala and Ektefa, Mohammadreza (2012) High level semantic concept retrieval using a hybrid similarity method. In: Knowledge Technology. Communications in Computer and Information Science (295). Springer, Berlin, pp. 262-271. ISBN 9783642328251; EISBN: 9783642328268 10.1007/978-3-642-32826-8_27
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
description In video search and retrieval, user’s need is expressed in terms of query. Early video retrieval systems usually matched video clips with such low-level features as color, shape, texture, and motion. In spite of the fact that retrieval is done accurately and automatically with such low-level features, the semantic meaning of the query cannot be expressed in this way. Moreover, the limitation of retrieval using desirable concept detectors is providing annotations for each concept. However, providing annotation for every concept in real world is very challenging and time consuming, and it is not possible to provide annotation for every concept in the real world. In this study, in order to improve the effectiveness of the retrieval, a method for similarity computation is proposed and experimented for mapping concepts whose annotations are not available onto the annotated and known concepts. The TRECVID 2005 data set is used to evaluate the effectiveness of the concept-based video retrieval model by applying the proposed similarity method. Results are also compared with previous similarity measures used in the same domain. The proposed similarity measure approach outperforms other methods with the Mean Average Precision (MAP) of 26.84% in concept retrieval.
author2 Lukose, Dickson
author_facet Lukose, Dickson
Kouchehbagh, Sara Memar
Affendey, Lilly Suriani
Mustapha, Norwati
C. Doraisamy, Shyamala
Ektefa, Mohammadreza
format Book Section
author Kouchehbagh, Sara Memar
Affendey, Lilly Suriani
Mustapha, Norwati
C. Doraisamy, Shyamala
Ektefa, Mohammadreza
spellingShingle Kouchehbagh, Sara Memar
Affendey, Lilly Suriani
Mustapha, Norwati
C. Doraisamy, Shyamala
Ektefa, Mohammadreza
High level semantic concept retrieval using a hybrid similarity method
author_sort Kouchehbagh, Sara Memar
title High level semantic concept retrieval using a hybrid similarity method
title_short High level semantic concept retrieval using a hybrid similarity method
title_full High level semantic concept retrieval using a hybrid similarity method
title_fullStr High level semantic concept retrieval using a hybrid similarity method
title_full_unstemmed High level semantic concept retrieval using a hybrid similarity method
title_sort high level semantic concept retrieval using a hybrid similarity method
publisher Springer
publishDate 2012
url http://psasir.upm.edu.my/id/eprint/26091/
_version_ 1643828827963523072
score 13.211869

Similar Items