A HVS-driven image segmentation framework using a local segmentation performance measure

Renbin Peng; Pramod K. Varshney

A HVS-driven image segmentation framework using a local segmentation performance measure

Department of Electrical Engineering & Computer Science

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

Abstract

This paper presents a novel framework for image segmentation. In this framework, image segmentation is considered to be a detection problem, and a "soft" segmentation objective function, in terms of the detection performance measure in local regions, is employed to guide the segmentation procedure. The human visual system information is also incorporated into the segmentation procedure to improve the efficiency of the framework by introducing a contrast sensitivity function-weighting operation in the wavelet domain. Encouraging experimental results are obtained when the algorithm is applied to real-world image data.

Original language	English (US)
Title of host publication	2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings
Pages	18-21
Number of pages	4
State	Published - Dec 1 2010
Event	2010 13th Western New York Image Processing Workshop, WNYIPW 2010 - Rochester, NY, United States Duration: Nov 5 2010 → Nov 5 2010

Publication series

Name	2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings

Other

Other	2010 13th Western New York Image Processing Workshop, WNYIPW 2010
Country	United States
City	Rochester, NY
Period	11/5/10 → 11/5/10

Keywords

Human visual system
Image segmentation
Markov random fields

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'A HVS-driven image segmentation framework using a local segmentation performance measure'. Together they form a unique fingerprint.

Cite this

A HVS-driven image segmentation framework using a local segmentation performance measure. / Peng, Renbin; Varshney, Pramod K.

2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings. 2010. p. 18-21 5649767 (2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings).

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

Peng, R & Varshney, PK 2010, A HVS-driven image segmentation framework using a local segmentation performance measure. in 2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings., 5649767, 2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings, pp. 18-21, 2010 13th Western New York Image Processing Workshop, WNYIPW 2010, Rochester, NY, United States, 11/5/10.

@inproceedings{ae1a5d60625146038d33e863ecea6da2,

title = "A HVS-driven image segmentation framework using a local segmentation performance measure",

abstract = "This paper presents a novel framework for image segmentation. In this framework, image segmentation is considered to be a detection problem, and a {"}soft{"} segmentation objective function, in terms of the detection performance measure in local regions, is employed to guide the segmentation procedure. The human visual system information is also incorporated into the segmentation procedure to improve the efficiency of the framework by introducing a contrast sensitivity function-weighting operation in the wavelet domain. Encouraging experimental results are obtained when the algorithm is applied to real-world image data.",

keywords = "Human visual system, Image segmentation, Markov random fields",

author = "Renbin Peng and Varshney, {Pramod K.}",

year = "2010",

month = dec,

day = "1",

language = "English (US)",

isbn = "9781424493005",

series = "2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings",

pages = "18--21",

booktitle = "2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings",

note = "2010 13th Western New York Image Processing Workshop, WNYIPW 2010 ; Conference date: 05-11-2010 Through 05-11-2010",

}

TY - GEN

T1 - A HVS-driven image segmentation framework using a local segmentation performance measure

AU - Peng, Renbin

AU - Varshney, Pramod K.

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This paper presents a novel framework for image segmentation. In this framework, image segmentation is considered to be a detection problem, and a "soft" segmentation objective function, in terms of the detection performance measure in local regions, is employed to guide the segmentation procedure. The human visual system information is also incorporated into the segmentation procedure to improve the efficiency of the framework by introducing a contrast sensitivity function-weighting operation in the wavelet domain. Encouraging experimental results are obtained when the algorithm is applied to real-world image data.

AB - This paper presents a novel framework for image segmentation. In this framework, image segmentation is considered to be a detection problem, and a "soft" segmentation objective function, in terms of the detection performance measure in local regions, is employed to guide the segmentation procedure. The human visual system information is also incorporated into the segmentation procedure to improve the efficiency of the framework by introducing a contrast sensitivity function-weighting operation in the wavelet domain. Encouraging experimental results are obtained when the algorithm is applied to real-world image data.

KW - Human visual system

KW - Image segmentation

KW - Markov random fields

UR - http://www.scopus.com/inward/record.url?scp=78650892699&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650892699&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78650892699

SN - 9781424493005

T3 - 2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings

SP - 18

EP - 21

BT - 2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings

T2 - 2010 13th Western New York Image Processing Workshop, WNYIPW 2010

Y2 - 5 November 2010 through 5 November 2010

ER -