Quaternion representation based visual saliency for stereoscopic image quality assessment

Xu WANG; Lin MA; Sam KWONG; Yu ZHOU

doi:10.1016/j.sigpro.2017.12.002

Quaternion representation based visual saliency for stereoscopic image quality assessment

Xu WANG, Lin MA, Sam KWONG, Yu ZHOU

Research output: Journal Publications › Journal Article (refereed) › peer-review

39 Citations (Scopus)

Abstract

In this paper, a novel visual saliency detection method for stereoscopic images is proposed for the stereoscopic image quality assessment (SIQA) by considering the disparity map and difference image between the stereo image pairs. Firstly, a new quaternion representation (QR) of each stereo image (left/right view image) is constructed, which comprises the image content, the inter-view disparity, and the difference map. The quaternion Fourier transform (QFT) is performed on the constructed QR to generate the visual saliency maps for left and right views of stereoscopic image pairs, respectively. The generated visual saliency maps are further incorporated into the quality metrics for SIQA. Experimental results demonstrate that the visual saliency maps generated by the proposed method can help significantly boost the performance of SIQA, comparing with other visual saliency models proposed for stereoscopic images. It further confirms that the proposed visual saliency model can accurate depict the acuity property of human visual system (HVS) in judging the perceptual quality of stereoscopic images.

Original language	English
Pages (from-to)	202-213
Journal	Signal Processing
Volume	145
Early online date	8 Dec 2017
DOIs	https://doi.org/10.1016/j.sigpro.2017.12.002
Publication status	Published - Apr 2018
Externally published	Yes

Bibliographical note

This work was supported in part by the Natural Science Foundation of China under Grants 61501299, 61672443, 61702336 and 61620106008, in part by the Guangdong Nature Science Foundation under Grant 2016A030310058, in part by Hong Kong RGC General Research Fund (GRF) 9042322 (CityU 11200116) and 9042489 (CityU 11206317), in part by the Shenzhen Emerging Industries of the Strategic Basic Research Project under Grants JCYJ20160226191842793 and JCYJ20170302154254147, in part by Natural Science Foundation of SZU (grant no. 2017031), in part by the Project 2016049 supported by SZU R/D Fund, in part by the Tencent “Rhinoceros Birds”-Scientific Research Foundation for Young Teachers of Shenzhen University, and in part by a grant from the Shenzhen Research Institute, City University of Hong Kong.

Keywords

Human visual system (HVS)
Quaternion representation (QR)
Stereoscopic image quality assessment (SIQA)
Visual saliency

Access to Document

10.1016/j.sigpro.2017.12.002

Cite this

@article{ec11f66dc65b490682820f28bfb341f3,

title = "Quaternion representation based visual saliency for stereoscopic image quality assessment",

abstract = "In this paper, a novel visual saliency detection method for stereoscopic images is proposed for the stereoscopic image quality assessment (SIQA) by considering the disparity map and difference image between the stereo image pairs. Firstly, a new quaternion representation (QR) of each stereo image (left/right view image) is constructed, which comprises the image content, the inter-view disparity, and the difference map. The quaternion Fourier transform (QFT) is performed on the constructed QR to generate the visual saliency maps for left and right views of stereoscopic image pairs, respectively. The generated visual saliency maps are further incorporated into the quality metrics for SIQA. Experimental results demonstrate that the visual saliency maps generated by the proposed method can help significantly boost the performance of SIQA, comparing with other visual saliency models proposed for stereoscopic images. It further confirms that the proposed visual saliency model can accurate depict the acuity property of human visual system (HVS) in judging the perceptual quality of stereoscopic images.",

keywords = "Human visual system (HVS), Quaternion representation (QR), Stereoscopic image quality assessment (SIQA), Visual saliency",

author = "Xu WANG and Lin MA and Sam KWONG and Yu ZHOU",

note = "This work was supported in part by the Natural Science Foundation of China under Grants 61501299, 61672443, 61702336 and 61620106008, in part by the Guangdong Nature Science Foundation under Grant 2016A030310058, in part by Hong Kong RGC General Research Fund (GRF) 9042322 (CityU 11200116) and 9042489 (CityU 11206317), in part by the Shenzhen Emerging Industries of the Strategic Basic Research Project under Grants JCYJ20160226191842793 and JCYJ20170302154254147, in part by Natural Science Foundation of SZU (grant no. 2017031), in part by the Project 2016049 supported by SZU R/D Fund, in part by the Tencent “Rhinoceros Birds”-Scientific Research Foundation for Young Teachers of Shenzhen University, and in part by a grant from the Shenzhen Research Institute, City University of Hong Kong.",

year = "2018",

month = apr,

doi = "10.1016/j.sigpro.2017.12.002",

language = "English",

volume = "145",

pages = "202--213",

journal = "Signal Processing",

issn = "0165-1684",

publisher = "Elsevier",

}

TY - JOUR

T1 - Quaternion representation based visual saliency for stereoscopic image quality assessment

AU - WANG, Xu

AU - MA, Lin

AU - KWONG, Sam

AU - ZHOU, Yu

N1 - This work was supported in part by the Natural Science Foundation of China under Grants 61501299, 61672443, 61702336 and 61620106008, in part by the Guangdong Nature Science Foundation under Grant 2016A030310058, in part by Hong Kong RGC General Research Fund (GRF) 9042322 (CityU 11200116) and 9042489 (CityU 11206317), in part by the Shenzhen Emerging Industries of the Strategic Basic Research Project under Grants JCYJ20160226191842793 and JCYJ20170302154254147, in part by Natural Science Foundation of SZU (grant no. 2017031), in part by the Project 2016049 supported by SZU R/D Fund, in part by the Tencent “Rhinoceros Birds”-Scientific Research Foundation for Young Teachers of Shenzhen University, and in part by a grant from the Shenzhen Research Institute, City University of Hong Kong.

PY - 2018/4

Y1 - 2018/4

N2 - In this paper, a novel visual saliency detection method for stereoscopic images is proposed for the stereoscopic image quality assessment (SIQA) by considering the disparity map and difference image between the stereo image pairs. Firstly, a new quaternion representation (QR) of each stereo image (left/right view image) is constructed, which comprises the image content, the inter-view disparity, and the difference map. The quaternion Fourier transform (QFT) is performed on the constructed QR to generate the visual saliency maps for left and right views of stereoscopic image pairs, respectively. The generated visual saliency maps are further incorporated into the quality metrics for SIQA. Experimental results demonstrate that the visual saliency maps generated by the proposed method can help significantly boost the performance of SIQA, comparing with other visual saliency models proposed for stereoscopic images. It further confirms that the proposed visual saliency model can accurate depict the acuity property of human visual system (HVS) in judging the perceptual quality of stereoscopic images.

AB - In this paper, a novel visual saliency detection method for stereoscopic images is proposed for the stereoscopic image quality assessment (SIQA) by considering the disparity map and difference image between the stereo image pairs. Firstly, a new quaternion representation (QR) of each stereo image (left/right view image) is constructed, which comprises the image content, the inter-view disparity, and the difference map. The quaternion Fourier transform (QFT) is performed on the constructed QR to generate the visual saliency maps for left and right views of stereoscopic image pairs, respectively. The generated visual saliency maps are further incorporated into the quality metrics for SIQA. Experimental results demonstrate that the visual saliency maps generated by the proposed method can help significantly boost the performance of SIQA, comparing with other visual saliency models proposed for stereoscopic images. It further confirms that the proposed visual saliency model can accurate depict the acuity property of human visual system (HVS) in judging the perceptual quality of stereoscopic images.

KW - Human visual system (HVS)

KW - Quaternion representation (QR)

KW - Stereoscopic image quality assessment (SIQA)

KW - Visual saliency

UR - http://www.scopus.com/inward/record.url?scp=85038008612&partnerID=8YFLogxK

U2 - 10.1016/j.sigpro.2017.12.002

DO - 10.1016/j.sigpro.2017.12.002

M3 - Journal Article (refereed)

SN - 0165-1684

VL - 145

SP - 202

EP - 213

JO - Signal Processing

JF - Signal Processing

ER -

Quaternion representation based visual saliency for stereoscopic image quality assessment

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this