An improved model of saliency-based visual attention using fuzzy interface system

Zahra Kouchaki; Ali Motie Nasrabadi; Keivan Maghooli

An improved model of saliency-based visual attention using fuzzy interface system

Zahra Kouchaki^*, Ali Motie Nasrabadi, Keivan Maghooli

^*Corresponding author for this work

Faculty of Medicine, Health and Human Sciences

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

3 Citations (Scopus)

Abstract

This study presents a novel method of generating saliency map in the basic saliency-based visual attention modeling proposed by Itti [1]. This can be applied in further processing such as object detection or recognition purpose. There are three conspicuity maps in saliency-based visual attention model which are derived from three different channels of color, intensity and orientation. The previous methods of generating saliency map are based on linear combination of these maps. Our proposed method employs Fuzzy Interface System (FIS) to combine three conspicuity maps instead of simple superposition which seems not reasonable biologically. Experimental results indicate the effectiveness of our proposed strategy in finding desired object with more accuracy in a datasets containing 32 images of emergency triangle with natural environment background. Furthermore, comparison with basic saliency model is provided to justify the capability of our proposed strategy.

Original language	English
Title of host publication	2011 6th International Conference on Computer Sciences and Convergence Information Technology (ICCIT 2011)
Editors	Franz I.S. Ko, Kae Dal Kwack, Soonwook Hwang, Shigeo Kawata, Yen-Wei Chen
Place of Publication	Piscataway, N.J.
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	204-207
Number of pages	4
ISBN (Electronic)	9788988678558
ISBN (Print)	9781457704727
Publication status	Published - Dec 2011
Event	6th International Conference on Computer Sciences and Convergence Information Technology, ICCIT - 2011 - Seogwipo, Jeju Island, Korea, Republic of Duration: 29 Nov 2011 → 1 Dec 2011

Other

Other	6th International Conference on Computer Sciences and Convergence Information Technology, ICCIT - 2011
Country/Territory	Korea, Republic of
City	Seogwipo, Jeju Island
Period	29/11/11 → 1/12/11

Keywords

conspicuity maps
fuzzy interface system
saliency-based visual attention

Cite this

Kouchaki, Z., Nasrabadi, A. M., & Maghooli, K. (2011). An improved model of saliency-based visual attention using fuzzy interface system. In F. I. S. Ko, K. D. Kwack, S. Hwang, S. Kawata, & Y.-W. Chen (Eds.), 2011 6th International Conference on Computer Sciences and Convergence Information Technology (ICCIT 2011) (pp. 204-207). Institute of Electrical and Electronics Engineers (IEEE).

Kouchaki, Zahra ; Nasrabadi, Ali Motie ; Maghooli, Keivan. / An improved model of saliency-based visual attention using fuzzy interface system. 2011 6th International Conference on Computer Sciences and Convergence Information Technology (ICCIT 2011). editor / Franz I.S. Ko ; Kae Dal Kwack ; Soonwook Hwang ; Shigeo Kawata ; Yen-Wei Chen. Piscataway, N.J. : Institute of Electrical and Electronics Engineers (IEEE), 2011. pp. 204-207

@inproceedings{219dc67e94d54dbba75df0d716d03eaa,

title = "An improved model of saliency-based visual attention using fuzzy interface system",

abstract = "This study presents a novel method of generating saliency map in the basic saliency-based visual attention modeling proposed by Itti [1]. This can be applied in further processing such as object detection or recognition purpose. There are three conspicuity maps in saliency-based visual attention model which are derived from three different channels of color, intensity and orientation. The previous methods of generating saliency map are based on linear combination of these maps. Our proposed method employs Fuzzy Interface System (FIS) to combine three conspicuity maps instead of simple superposition which seems not reasonable biologically. Experimental results indicate the effectiveness of our proposed strategy in finding desired object with more accuracy in a datasets containing 32 images of emergency triangle with natural environment background. Furthermore, comparison with basic saliency model is provided to justify the capability of our proposed strategy.",

keywords = "conspicuity maps, fuzzy interface system, saliency-based visual attention",

author = "Zahra Kouchaki and Nasrabadi, {Ali Motie} and Keivan Maghooli",

year = "2011",

month = dec,

language = "English",

isbn = "9781457704727",

pages = "204--207",

editor = "Ko, {Franz I.S.} and Kwack, {Kae Dal} and Soonwook Hwang and Shigeo Kawata and Yen-Wei Chen",

booktitle = "2011 6th International Conference on Computer Sciences and Convergence Information Technology (ICCIT 2011)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "6th International Conference on Computer Sciences and Convergence Information Technology, ICCIT - 2011 ; Conference date: 29-11-2011 Through 01-12-2011",

}

Kouchaki, Z, Nasrabadi, AM & Maghooli, K 2011, An improved model of saliency-based visual attention using fuzzy interface system. in FIS Ko, KD Kwack, S Hwang, S Kawata & Y-W Chen (eds), 2011 6th International Conference on Computer Sciences and Convergence Information Technology (ICCIT 2011). Institute of Electrical and Electronics Engineers (IEEE), Piscataway, N.J., pp. 204-207, 6th International Conference on Computer Sciences and Convergence Information Technology, ICCIT - 2011, Seogwipo, Jeju Island, Korea, Republic of, 29/11/11.

An improved model of saliency-based visual attention using fuzzy interface system. / Kouchaki, Zahra; Nasrabadi, Ali Motie; Maghooli, Keivan.
2011 6th International Conference on Computer Sciences and Convergence Information Technology (ICCIT 2011). ed. / Franz I.S. Ko; Kae Dal Kwack; Soonwook Hwang; Shigeo Kawata; Yen-Wei Chen. Piscataway, N.J.: Institute of Electrical and Electronics Engineers (IEEE), 2011. p. 204-207.

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

TY - GEN

T1 - An improved model of saliency-based visual attention using fuzzy interface system

AU - Kouchaki, Zahra

AU - Nasrabadi, Ali Motie

AU - Maghooli, Keivan

PY - 2011/12

Y1 - 2011/12

N2 - This study presents a novel method of generating saliency map in the basic saliency-based visual attention modeling proposed by Itti [1]. This can be applied in further processing such as object detection or recognition purpose. There are three conspicuity maps in saliency-based visual attention model which are derived from three different channels of color, intensity and orientation. The previous methods of generating saliency map are based on linear combination of these maps. Our proposed method employs Fuzzy Interface System (FIS) to combine three conspicuity maps instead of simple superposition which seems not reasonable biologically. Experimental results indicate the effectiveness of our proposed strategy in finding desired object with more accuracy in a datasets containing 32 images of emergency triangle with natural environment background. Furthermore, comparison with basic saliency model is provided to justify the capability of our proposed strategy.

AB - This study presents a novel method of generating saliency map in the basic saliency-based visual attention modeling proposed by Itti [1]. This can be applied in further processing such as object detection or recognition purpose. There are three conspicuity maps in saliency-based visual attention model which are derived from three different channels of color, intensity and orientation. The previous methods of generating saliency map are based on linear combination of these maps. Our proposed method employs Fuzzy Interface System (FIS) to combine three conspicuity maps instead of simple superposition which seems not reasonable biologically. Experimental results indicate the effectiveness of our proposed strategy in finding desired object with more accuracy in a datasets containing 32 images of emergency triangle with natural environment background. Furthermore, comparison with basic saliency model is provided to justify the capability of our proposed strategy.

KW - conspicuity maps

KW - fuzzy interface system

KW - saliency-based visual attention

UR - http://www.scopus.com/inward/record.url?scp=84862124058&partnerID=8YFLogxK

M3 - Conference proceeding contribution

AN - SCOPUS:84862124058

SN - 9781457704727

SP - 204

EP - 207

BT - 2011 6th International Conference on Computer Sciences and Convergence Information Technology (ICCIT 2011)

A2 - Ko, Franz I.S.

A2 - Kwack, Kae Dal

A2 - Hwang, Soonwook

A2 - Kawata, Shigeo

A2 - Chen, Yen-Wei

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, N.J.

T2 - 6th International Conference on Computer Sciences and Convergence Information Technology, ICCIT - 2011

Y2 - 29 November 2011 through 1 December 2011

ER -

Kouchaki Z, Nasrabadi AM, Maghooli K. An improved model of saliency-based visual attention using fuzzy interface system. In Ko FIS, Kwack KD, Hwang S, Kawata S, Chen YW, editors, 2011 6th International Conference on Computer Sciences and Convergence Information Technology (ICCIT 2011). Piscataway, N.J.: Institute of Electrical and Electronics Engineers (IEEE). 2011. p. 204-207

An improved model of saliency-based visual attention using fuzzy interface system

Abstract

Other

Keywords

Other files and links

Fingerprint

Cite this