Image annotation fusing content-based and tag-based technique using support vector machine and vector space model

Shan Bin Chan; Hayato Yamana; Duy Dinh Le; Shinichi Satoh

doi:10.1109/SITIS.2014.76

Image annotation fusing content-based and tag-based technique using support vector machine and vector space model

Shan Bin Chan, Hayato Yamana, Duy Dinh Le, Shinichi Satoh

School of Fundamental Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

In this paper, we propose a new image annotation method by combining content-based image annotation and tag-based image annotation techniques. Content-based image annotation technique is adopted to extract 'loosely defined concepts' by analyzing pre-given images' features such as color moment (CM), edge orientation histogram (EOH), and local binary pattern (LBP), followed by constructing a set of SVMs for 100 loosely defined concepts. A base-vector for each concept, similar to tag-based image annotation technique, is then constructed by using SVMs' predicted probabilistic results for sample-images whose main concepts are known. Finally cosine similarity between a query-image vector and the base vector is calculated for each concept. Experimental results show that our proposed method outperforms content-based image annotation technique by about 23% in accuracy.

Original language	English
Title of host publication	Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014
Editors	Richard Chbeir, Richard Chbeir, Kokou Yetongnon, Albert Dipanda
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	272-276
Number of pages	5
ISBN (Electronic)	9781479979783
DOIs	https://doi.org/10.1109/SITIS.2014.76
Publication status	Published - 2014
Event	10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014 - Marrakech, Morocco Duration: 2014 Nov 23 → 2014 Nov 27

Publication series

Name	Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014

Other

Other	10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014
Country/Territory	Morocco
City	Marrakech
Period	14/11/23 → 14/11/27

Keywords

image annotation
support vector machine
vector space model

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Signal Processing
Computer Networks and Communications

Access to Document

10.1109/SITIS.2014.76

Cite this

Chan, S. B., Yamana, H., Le, D. D., & Satoh, S. (2014). Image annotation fusing content-based and tag-based technique using support vector machine and vector space model. In R. Chbeir, R. Chbeir, K. Yetongnon, & A. Dipanda (Eds.), Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014 (pp. 272-276). Article 7081558 (Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SITIS.2014.76

Image annotation fusing content-based and tag-based technique using support vector machine and vector space model. / Chan, Shan Bin; Yamana, Hayato; Le, Duy Dinh et al.
Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014. ed. / Richard Chbeir; Richard Chbeir; Kokou Yetongnon; Albert Dipanda. Institute of Electrical and Electronics Engineers Inc., 2014. p. 272-276 7081558 (Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Chan, SB, Yamana, H, Le, DD & Satoh, S 2014, Image annotation fusing content-based and tag-based technique using support vector machine and vector space model. in R Chbeir, R Chbeir, K Yetongnon & A Dipanda (eds), Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014., 7081558, Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014, Institute of Electrical and Electronics Engineers Inc., pp. 272-276, 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014, Marrakech, Morocco, 14/11/23. https://doi.org/10.1109/SITIS.2014.76

Chan SB, Yamana H, Le DD, Satoh S. Image annotation fusing content-based and tag-based technique using support vector machine and vector space model. In Chbeir R, Chbeir R, Yetongnon K, Dipanda A, editors, Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 272-276. 7081558. (Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014). doi: 10.1109/SITIS.2014.76

Chan, Shan Bin ; Yamana, Hayato ; Le, Duy Dinh et al. / Image annotation fusing content-based and tag-based technique using support vector machine and vector space model. Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014. editor / Richard Chbeir ; Richard Chbeir ; Kokou Yetongnon ; Albert Dipanda. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 272-276 (Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014).

@inproceedings{fc1160e533574bef82c229e73d7f6223,

title = "Image annotation fusing content-based and tag-based technique using support vector machine and vector space model",

abstract = "In this paper, we propose a new image annotation method by combining content-based image annotation and tag-based image annotation techniques. Content-based image annotation technique is adopted to extract 'loosely defined concepts' by analyzing pre-given images' features such as color moment (CM), edge orientation histogram (EOH), and local binary pattern (LBP), followed by constructing a set of SVMs for 100 loosely defined concepts. A base-vector for each concept, similar to tag-based image annotation technique, is then constructed by using SVMs' predicted probabilistic results for sample-images whose main concepts are known. Finally cosine similarity between a query-image vector and the base vector is calculated for each concept. Experimental results show that our proposed method outperforms content-based image annotation technique by about 23% in accuracy.",

keywords = "image annotation, support vector machine, vector space model",

author = "Chan, {Shan Bin} and Hayato Yamana and Le, {Duy Dinh} and Shinichi Satoh",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014 ; Conference date: 23-11-2014 Through 27-11-2014",

year = "2014",

doi = "10.1109/SITIS.2014.76",

language = "English",

series = "Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "272--276",

editor = "Richard Chbeir and Richard Chbeir and Kokou Yetongnon and Albert Dipanda",

booktitle = "Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014",

}

TY - GEN

T1 - Image annotation fusing content-based and tag-based technique using support vector machine and vector space model

AU - Chan, Shan Bin

AU - Yamana, Hayato

AU - Le, Duy Dinh

AU - Satoh, Shinichi

PY - 2014

Y1 - 2014

N2 - In this paper, we propose a new image annotation method by combining content-based image annotation and tag-based image annotation techniques. Content-based image annotation technique is adopted to extract 'loosely defined concepts' by analyzing pre-given images' features such as color moment (CM), edge orientation histogram (EOH), and local binary pattern (LBP), followed by constructing a set of SVMs for 100 loosely defined concepts. A base-vector for each concept, similar to tag-based image annotation technique, is then constructed by using SVMs' predicted probabilistic results for sample-images whose main concepts are known. Finally cosine similarity between a query-image vector and the base vector is calculated for each concept. Experimental results show that our proposed method outperforms content-based image annotation technique by about 23% in accuracy.

AB - In this paper, we propose a new image annotation method by combining content-based image annotation and tag-based image annotation techniques. Content-based image annotation technique is adopted to extract 'loosely defined concepts' by analyzing pre-given images' features such as color moment (CM), edge orientation histogram (EOH), and local binary pattern (LBP), followed by constructing a set of SVMs for 100 loosely defined concepts. A base-vector for each concept, similar to tag-based image annotation technique, is then constructed by using SVMs' predicted probabilistic results for sample-images whose main concepts are known. Finally cosine similarity between a query-image vector and the base vector is calculated for each concept. Experimental results show that our proposed method outperforms content-based image annotation technique by about 23% in accuracy.

KW - image annotation

KW - support vector machine

KW - vector space model

UR - http://www.scopus.com/inward/record.url?scp=84988227368&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988227368&partnerID=8YFLogxK

U2 - 10.1109/SITIS.2014.76

DO - 10.1109/SITIS.2014.76

M3 - Conference contribution

AN - SCOPUS:84988227368

T3 - Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014

SP - 272

EP - 276

BT - Proceedings - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014

A2 - Chbeir, Richard

A2 - Yetongnon, Kokou

A2 - Dipanda, Albert

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2014

Y2 - 23 November 2014 through 27 November 2014

ER -

Image annotation fusing content-based and tag-based technique using support vector machine and vector space model

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this