Saliency detection using texture and local cues

Qiang Qi; Muwei Jian; Yilong Yin; Junyu Dong; Wenyin Zhang; Hui Yu

doi:10.1007/978-981-10-7305-2_58

Saliency detection using texture and local cues

Qiang Qi, Muwei Jian, Yilong Yin, Junyu Dong, Wenyin Zhang, Hui Yu

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

457 Downloads (Pure)

Abstract

In this paper, a simple but effective method is proposed for detecting salient objects by utilizing texture and local cues. In contrast to the existing saliency detection models, which mainly consider visual features such as orientation, color, and shape information, our proposed method takes the significant texture cue into consideration to guarantee the accuracy of the detected salient regions. Firstly, an effective method based on selective contrast (SC), which explores the most distinguishable component information in texture, is used to calculate the texture saliency map. Then, we detect local saliency by using a locality-constrained linear coding algorithm. Finally, the output saliency map is computed by integrating texture and local saliency cues simultaneously. Experimental results, based on a widely used and openly available database, demonstrate that the proposed method can produce competitive results and outperforms some existing popular methods.

Original language	English
Title of host publication	Computer Vision
Subtitle of host publication	Second CCF Chinese Conference, CCCV 2017, Tianjin, China, October 11–14, 2017, Proceedings, Part III
Editors	Jinfeng Yang, Qinghua Hu, Ming-Ming Cheng, Liang Wang, Qingshan Liu, Xiang Bai, Deyu Meng
Publisher	Springer
Pages	689-699
ISBN (Electronic)	978-981-10-7305-2
ISBN (Print)	978-981-10-7304-5
DOIs	https://doi.org/10.1007/978-981-10-7305-2_58
Publication status	Published - Dec 2017
Event	CCF Chinese Conference on Computer Vision - Tianjin, China Duration: 11 Oct 2017 → 14 Oct 2017

Publication series

Name	Communications in Computer and Information Science
Publisher	Springer
Volume	773
ISSN (Print)	1865-0929

Conference

Conference	CCF Chinese Conference on Computer Vision
Abbreviated title	CCCV 2017
Country/Territory	China
City	Tianjin
Period	11/10/17 → 14/10/17

Access to Document

10.1007/978-981-10-7305-2_58

Saliency detection using texture and local cues
The final authenticated version is available online at https://doi.org/10.1007/978-981-10-7305-2_58.
Accepted author manuscript (Post-print), 391 KB

Cite this

Qi, Q., Jian, M., Yin, Y., Dong, J., Zhang, W., & Yu, H. (2017). Saliency detection using texture and local cues. In J. Yang, Q. Hu, M.-M. Cheng, L. Wang, Q. Liu, X. Bai, & D. Meng (Eds.), Computer Vision: Second CCF Chinese Conference, CCCV 2017, Tianjin, China, October 11–14, 2017, Proceedings, Part III (pp. 689-699). (Communications in Computer and Information Science; Vol. 773). Springer. https://doi.org/10.1007/978-981-10-7305-2_58

Qi, Qiang ; Jian, Muwei ; Yin, Yilong et al. / Saliency detection using texture and local cues. Computer Vision: Second CCF Chinese Conference, CCCV 2017, Tianjin, China, October 11–14, 2017, Proceedings, Part III. editor / Jinfeng Yang ; Qinghua Hu ; Ming-Ming Cheng ; Liang Wang ; Qingshan Liu ; Xiang Bai ; Deyu Meng. Springer, 2017. pp. 689-699 (Communications in Computer and Information Science).

@inproceedings{8603904770d94d29a637fb221d5029de,

title = "Saliency detection using texture and local cues",

abstract = "In this paper, a simple but effective method is proposed for detecting salient objects by utilizing texture and local cues. In contrast to the existing saliency detection models, which mainly consider visual features such as orientation, color, and shape information, our proposed method takes the significant texture cue into consideration to guarantee the accuracy of the detected salient regions. Firstly, an effective method based on selective contrast (SC), which explores the most distinguishable component information in texture, is used to calculate the texture saliency map. Then, we detect local saliency by using a locality-constrained linear coding algorithm. Finally, the output saliency map is computed by integrating texture and local saliency cues simultaneously. Experimental results, based on a widely used and openly available database, demonstrate that the proposed method can produce competitive results and outperforms some existing popular methods.",

author = "Qiang Qi and Muwei Jian and Yilong Yin and Junyu Dong and Wenyin Zhang and Hui Yu",

year = "2017",

month = dec,

doi = "10.1007/978-981-10-7305-2_58",

language = "English",

isbn = "978-981-10-7304-5",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "689--699",

editor = "Jinfeng Yang and Qinghua Hu and Ming-Ming Cheng and Liang Wang and Qingshan Liu and Xiang Bai and Deyu Meng",

booktitle = "Computer Vision",

note = "CCF Chinese Conference on Computer Vision, CCCV 2017 ; Conference date: 11-10-2017 Through 14-10-2017",

}

Qi, Q, Jian, M, Yin, Y, Dong, J, Zhang, W & Yu, H 2017, Saliency detection using texture and local cues. in J Yang, Q Hu, M-M Cheng, L Wang, Q Liu, X Bai & D Meng (eds), Computer Vision: Second CCF Chinese Conference, CCCV 2017, Tianjin, China, October 11–14, 2017, Proceedings, Part III. Communications in Computer and Information Science, vol. 773, Springer, pp. 689-699, CCF Chinese Conference on Computer Vision, Tianjin, China, 11/10/17. https://doi.org/10.1007/978-981-10-7305-2_58

Saliency detection using texture and local cues. / Qi, Qiang; Jian, Muwei; Yin, Yilong et al.
Computer Vision: Second CCF Chinese Conference, CCCV 2017, Tianjin, China, October 11–14, 2017, Proceedings, Part III. ed. / Jinfeng Yang; Qinghua Hu; Ming-Ming Cheng; Liang Wang; Qingshan Liu; Xiang Bai; Deyu Meng. Springer, 2017. p. 689-699 (Communications in Computer and Information Science; Vol. 773).

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

TY - GEN

T1 - Saliency detection using texture and local cues

AU - Qi, Qiang

AU - Jian, Muwei

AU - Yin, Yilong

AU - Dong, Junyu

AU - Zhang, Wenyin

AU - Yu, Hui

PY - 2017/12

Y1 - 2017/12

N2 - In this paper, a simple but effective method is proposed for detecting salient objects by utilizing texture and local cues. In contrast to the existing saliency detection models, which mainly consider visual features such as orientation, color, and shape information, our proposed method takes the significant texture cue into consideration to guarantee the accuracy of the detected salient regions. Firstly, an effective method based on selective contrast (SC), which explores the most distinguishable component information in texture, is used to calculate the texture saliency map. Then, we detect local saliency by using a locality-constrained linear coding algorithm. Finally, the output saliency map is computed by integrating texture and local saliency cues simultaneously. Experimental results, based on a widely used and openly available database, demonstrate that the proposed method can produce competitive results and outperforms some existing popular methods.

AB - In this paper, a simple but effective method is proposed for detecting salient objects by utilizing texture and local cues. In contrast to the existing saliency detection models, which mainly consider visual features such as orientation, color, and shape information, our proposed method takes the significant texture cue into consideration to guarantee the accuracy of the detected salient regions. Firstly, an effective method based on selective contrast (SC), which explores the most distinguishable component information in texture, is used to calculate the texture saliency map. Then, we detect local saliency by using a locality-constrained linear coding algorithm. Finally, the output saliency map is computed by integrating texture and local saliency cues simultaneously. Experimental results, based on a widely used and openly available database, demonstrate that the proposed method can produce competitive results and outperforms some existing popular methods.

U2 - 10.1007/978-981-10-7305-2_58

DO - 10.1007/978-981-10-7305-2_58

M3 - Conference contribution

SN - 978-981-10-7304-5

T3 - Communications in Computer and Information Science

SP - 689

EP - 699

BT - Computer Vision

A2 - Yang, Jinfeng

A2 - Hu, Qinghua

A2 - Cheng, Ming-Ming

A2 - Wang, Liang

A2 - Liu, Qingshan

A2 - Bai, Xiang

A2 - Meng, Deyu

PB - Springer

T2 - CCF Chinese Conference on Computer Vision

Y2 - 11 October 2017 through 14 October 2017

ER -

Qi Q, Jian M, Yin Y, Dong J, Zhang W, Yu H. Saliency detection using texture and local cues. In Yang J, Hu Q, Cheng MM, Wang L, Liu Q, Bai X, Meng D, editors, Computer Vision: Second CCF Chinese Conference, CCCV 2017, Tianjin, China, October 11–14, 2017, Proceedings, Part III. Springer. 2017. p. 689-699. (Communications in Computer and Information Science). Epub 2017 Dec 8. doi: 10.1007/978-981-10-7305-2_58

Saliency detection using texture and local cues

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this