Unsupervised Saliency Detection Based on 2D Gabor and Curvelets Transforms

Sheng-hua Zhong; Yan Liu; Ling Shao; Gangshan Wu

doi:10.1145/2043674.2043716

Unsupervised Saliency Detection Based on 2D Gabor and Curvelets Transforms

Sheng-hua Zhong, Yan Liu, Ling Shao, Gangshan Wu

Computer Information Sciences Department

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

2 Citations (Scopus)

Abstract

Construction of saliency map in multimedia data is useful for applications in multimedia like object segmentation, quality assessment, and object recognition. In this paper, we propose a novel saliency map model called Gabor & Curvelets based Saliency Map (GCSMP) relying on 2D Gabor and Curvelet transforms. Compared with the traditional model based on DOG and wavelets, our model takes advantage of Gabor transform's spatial localization and Curvelet transform's edge and directional information. We also discuss the influence of center bias and object detectors in our model. Empirical validations on standard dataset demonstrate the effectiveness of the proposed technique.

Original language	English
Title of host publication	ICIMCS '11: Proceedings of the Third International Conference on Internet Multimedia Computing and Service
Place of Publication	New York, NY, United States
Publisher	ACM
Pages	146–149
ISBN (Print)	9781450309189
DOIs	https://doi.org/10.1145/2043674.2043716
Publication status	Published - 5 Aug 2011
Event	ICIMCS '11 - The Third International Conference on Internet Multimedia Computing and Service - Chengdu, China Duration: 1 Aug 2011 → …

Conference

Conference	ICIMCS '11 - The Third International Conference on Internet Multimedia Computing and Service
Period	1/08/11 → …

Keywords

Saliency map
2D Gabor
Curvelet transform

Access to Document

10.1145/2043674.2043716

Cite this

@inproceedings{fce07d5ed4e24cfea5c9f0449f61f826,

title = "Unsupervised Saliency Detection Based on 2D Gabor and Curvelets Transforms",

abstract = "Construction of saliency map in multimedia data is useful for applications in multimedia like object segmentation, quality assessment, and object recognition. In this paper, we propose a novel saliency map model called Gabor & Curvelets based Saliency Map (GCSMP) relying on 2D Gabor and Curvelet transforms. Compared with the traditional model based on DOG and wavelets, our model takes advantage of Gabor transform's spatial localization and Curvelet transform's edge and directional information. We also discuss the influence of center bias and object detectors in our model. Empirical validations on standard dataset demonstrate the effectiveness of the proposed technique.",

keywords = "Saliency map, 2D Gabor, Curvelet transform",

author = "Sheng-hua Zhong and Yan Liu and Ling Shao and Gangshan Wu",

year = "2011",

month = aug,

day = "5",

doi = "10.1145/2043674.2043716",

language = "English",

isbn = "9781450309189",

pages = "146–149",

booktitle = "ICIMCS '11: Proceedings of the Third International Conference on Internet Multimedia Computing and Service",

publisher = "ACM",

address = "United States",

note = "ICIMCS '11 - The Third International Conference on Internet Multimedia Computing and Service ; Conference date: 01-08-2011",

}

Zhong, S, Liu, Y, Shao, L & Wu, G 2011, Unsupervised Saliency Detection Based on 2D Gabor and Curvelets Transforms. in ICIMCS '11: Proceedings of the Third International Conference on Internet Multimedia Computing and Service. ACM, New York, NY, United States, pp. 146–149, ICIMCS '11 - The Third International Conference on Internet Multimedia Computing and Service, 1/08/11. https://doi.org/10.1145/2043674.2043716

Unsupervised Saliency Detection Based on 2D Gabor and Curvelets Transforms. / Zhong, Sheng-hua; Liu, Yan; Shao, Ling et al.
ICIMCS '11: Proceedings of the Third International Conference on Internet Multimedia Computing and Service. New York, NY, United States: ACM, 2011. p. 146–149.

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

TY - GEN

T1 - Unsupervised Saliency Detection Based on 2D Gabor and Curvelets Transforms

AU - Zhong, Sheng-hua

AU - Liu, Yan

AU - Shao, Ling

AU - Wu, Gangshan

PY - 2011/8/5

Y1 - 2011/8/5

N2 - Construction of saliency map in multimedia data is useful for applications in multimedia like object segmentation, quality assessment, and object recognition. In this paper, we propose a novel saliency map model called Gabor & Curvelets based Saliency Map (GCSMP) relying on 2D Gabor and Curvelet transforms. Compared with the traditional model based on DOG and wavelets, our model takes advantage of Gabor transform's spatial localization and Curvelet transform's edge and directional information. We also discuss the influence of center bias and object detectors in our model. Empirical validations on standard dataset demonstrate the effectiveness of the proposed technique.

AB - Construction of saliency map in multimedia data is useful for applications in multimedia like object segmentation, quality assessment, and object recognition. In this paper, we propose a novel saliency map model called Gabor & Curvelets based Saliency Map (GCSMP) relying on 2D Gabor and Curvelet transforms. Compared with the traditional model based on DOG and wavelets, our model takes advantage of Gabor transform's spatial localization and Curvelet transform's edge and directional information. We also discuss the influence of center bias and object detectors in our model. Empirical validations on standard dataset demonstrate the effectiveness of the proposed technique.

KW - Saliency map

KW - 2D Gabor

KW - Curvelet transform

U2 - 10.1145/2043674.2043716

DO - 10.1145/2043674.2043716

M3 - Conference contribution

SN - 9781450309189

SP - 146

EP - 149

BT - ICIMCS '11: Proceedings of the Third International Conference on Internet Multimedia Computing and Service

PB - ACM

CY - New York, NY, United States

T2 - ICIMCS '11 - The Third International Conference on Internet Multimedia Computing and Service

Y2 - 1 August 2011

ER -