Saliency detection via combining global shape and local cue estimation

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

doi:10.1007/978-3-319-67777-4_28

Saliency detection via combining global shape and local cue estimation

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

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

323 Downloads (Pure)

Abstract

Recently, saliency detection has become a hot issue in computer vision. In this paper, a novel framework for image saliency detection is introduced by modeling global shape and local cue estimation simultaneously. Firstly, Quaternionic Distance Based Weber Descriptor (QDWD), which was initially designed for detecting outliers in color images, is used to model the salient object shape in an image. Secondly, we detect local saliency based on the reconstruction error by using a locality-constrained linear coding algorithm. Finally, by integrating global shape with local cue, a reliable saliency map can be computed and estimated. Experimental results, based on two widely used and openly available databases, show that the proposed method can produce reliable and promising results, compared to other state-of-the-art saliency detection algorithms.

Original language	English
Title of host publication	Intelligence Science and Big Data Engineering
Editors	Y. Sun, L. Zhang, J. Yang, H. Huang
Publisher	Springer
Pages	325-334
Number of pages	10
ISBN (Electronic)	978-3319677774
ISBN (Print)	978-3319677767
DOIs	https://doi.org/10.1007/978-3-319-67777-4_28
Publication status	Published - 14 Sept 2017
Event	IScIDE 2017: International Conference on Intelligence Science and Big Data Engineering - Dalian, China Duration: 23 Sept 2017 → 24 Sept 2017

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	10559
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	IScIDE 2017: International Conference on Intelligence Science and Big Data Engineering
Country/Territory	China
City	Dalian
Period	23/09/17 → 24/09/17

Keywords

saliency detection
QDWD
locality-constrained linear coding
local cue

Access to Document

10.1007/978-3-319-67777-4_28

IScIDE_2017_postprint(1)
This is a post-peer-review, pre-copyedit version of an article published in Intelligence Science and Big Data Engineering. IScIDE 2017. LEcture Notes in Computer Science, vol 10559.. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-319-67777-4_28.
Accepted author manuscript (Post-print), 605 KB

Cite this

@inproceedings{a7e9f0beb17e41ff97a1acfece18896c,

title = "Saliency detection via combining global shape and local cue estimation",

abstract = "Recently, saliency detection has become a hot issue in computer vision. In this paper, a novel framework for image saliency detection is introduced by modeling global shape and local cue estimation simultaneously. Firstly, Quaternionic Distance Based Weber Descriptor (QDWD), which was initially designed for detecting outliers in color images, is used to model the salient object shape in an image. Secondly, we detect local saliency based on the reconstruction error by using a locality-constrained linear coding algorithm. Finally, by integrating global shape with local cue, a reliable saliency map can be computed and estimated. Experimental results, based on two widely used and openly available databases, show that the proposed method can produce reliable and promising results, compared to other state-of-the-art saliency detection algorithms.",

keywords = "saliency detection, QDWD, locality-constrained linear coding, local cue",

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

year = "2017",

month = sep,

day = "14",

doi = "10.1007/978-3-319-67777-4\_28",

language = "English",

isbn = "978-3319677767",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "325--334",

editor = "Y. Sun and L. Zhang and J. Yang and H. Huang",

booktitle = "Intelligence Science and Big Data Engineering",

address = "Netherlands",

note = "IScIDE 2017: International Conference on Intelligence Science and Big Data Engineering ; Conference date: 23-09-2017 Through 24-09-2017",

}

Qi, Q, Jian, M, Yin, Y, Dong, J, Zhang, W & Yu, H 2017, Saliency detection via combining global shape and local cue estimation. in Y Sun, L Zhang, J Yang & H Huang (eds), Intelligence Science and Big Data Engineering. Lecture Notes in Computer Science, vol. 10559, Springer, pp. 325-334, IScIDE 2017: International Conference on Intelligence Science and Big Data Engineering, Dalian, China, 23/09/17. https://doi.org/10.1007/978-3-319-67777-4_28

Saliency detection via combining global shape and local cue estimation. / Qi, Qiang; Jian, Muwei; Yin, Yikang et al.
Intelligence Science and Big Data Engineering. ed. / Y. Sun; L. Zhang; J. Yang; H. Huang. Springer, 2017. p. 325-334 (Lecture Notes in Computer Science; Vol. 10559).

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

TY - GEN

T1 - Saliency detection via combining global shape and local cue estimation

AU - Qi, Qiang

AU - Jian, Muwei

AU - Yin, Yikang

AU - Dong, Junyu

AU - Zhang, Wenyin

AU - Yu, Hui

PY - 2017/9/14

Y1 - 2017/9/14

N2 - Recently, saliency detection has become a hot issue in computer vision. In this paper, a novel framework for image saliency detection is introduced by modeling global shape and local cue estimation simultaneously. Firstly, Quaternionic Distance Based Weber Descriptor (QDWD), which was initially designed for detecting outliers in color images, is used to model the salient object shape in an image. Secondly, we detect local saliency based on the reconstruction error by using a locality-constrained linear coding algorithm. Finally, by integrating global shape with local cue, a reliable saliency map can be computed and estimated. Experimental results, based on two widely used and openly available databases, show that the proposed method can produce reliable and promising results, compared to other state-of-the-art saliency detection algorithms.

AB - Recently, saliency detection has become a hot issue in computer vision. In this paper, a novel framework for image saliency detection is introduced by modeling global shape and local cue estimation simultaneously. Firstly, Quaternionic Distance Based Weber Descriptor (QDWD), which was initially designed for detecting outliers in color images, is used to model the salient object shape in an image. Secondly, we detect local saliency based on the reconstruction error by using a locality-constrained linear coding algorithm. Finally, by integrating global shape with local cue, a reliable saliency map can be computed and estimated. Experimental results, based on two widely used and openly available databases, show that the proposed method can produce reliable and promising results, compared to other state-of-the-art saliency detection algorithms.

KW - saliency detection

KW - QDWD

KW - locality-constrained linear coding

KW - local cue

U2 - 10.1007/978-3-319-67777-4_28

DO - 10.1007/978-3-319-67777-4_28

M3 - Conference contribution

SN - 978-3319677767

T3 - Lecture Notes in Computer Science

SP - 325

EP - 334

BT - Intelligence Science and Big Data Engineering

A2 - Sun, Y.

A2 - Zhang, L.

A2 - Yang, J.

A2 - Huang, H.

PB - Springer

T2 - IScIDE 2017: International Conference on Intelligence Science and Big Data Engineering

Y2 - 23 September 2017 through 24 September 2017

ER -

Saliency detection via combining global shape and local cue estimation

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this