Complex singular value decomposition based stereoscopic image quality assessment

Xu WANG; Lei CAO; Lin MA; Yu ZHOU; Sam KWONG

doi:10.1109/VCIP.2016.7805497

Complex singular value decomposition based stereoscopic image quality assessment

Xu WANG, Lei CAO, Lin MA, Yu ZHOU, Sam KWONG

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

2 Citations (Scopus)

Abstract

Designing a reliable and generic perceptual quality metric is a challenging issue in three-dimensional (3D) visual signal processing. Due to the limited knowledge on 3D perceptual, it is difficult to fuse the visual information of left and right views in an effective way. In this paper, we propose a complex singular value decomposition (CSVD) based stereoscopic image quality assessment (SIQA) metric. First, the corresponding blocks of the left/right view are grouped into complex representation (CR) block through the scale-invariant feature transform (SIFT) view matching process. Then we compute the CSVD coefficients of each CR block. Final, a CSVD based quality pooling stage is employed to predict the final visual quality of the distorted 3D image. Experimental results demonstrate that the proposed metric has good consistency with 3D perception of human.

Original language	English
Title of host publication	VCIP 2016 - 30th Anniversary of Visual Communication and Image Processing
DOIs	https://doi.org/10.1109/VCIP.2016.7805497
Publication status	Published - Nov 2016
Externally published	Yes

Keywords

Complex Singular Value Decomposition
Stereoscopic Image Quality Assessment

Access to Document

10.1109/VCIP.2016.7805497

Cite this

@inproceedings{7d28d780963b4034a90c161363942259,

title = "Complex singular value decomposition based stereoscopic image quality assessment",

abstract = "Designing a reliable and generic perceptual quality metric is a challenging issue in three-dimensional (3D) visual signal processing. Due to the limited knowledge on 3D perceptual, it is difficult to fuse the visual information of left and right views in an effective way. In this paper, we propose a complex singular value decomposition (CSVD) based stereoscopic image quality assessment (SIQA) metric. First, the corresponding blocks of the left/right view are grouped into complex representation (CR) block through the scale-invariant feature transform (SIFT) view matching process. Then we compute the CSVD coefficients of each CR block. Final, a CSVD based quality pooling stage is employed to predict the final visual quality of the distorted 3D image. Experimental results demonstrate that the proposed metric has good consistency with 3D perception of human.",

keywords = "Complex Singular Value Decomposition, Stereoscopic Image Quality Assessment",

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

year = "2016",

month = nov,

doi = "10.1109/VCIP.2016.7805497",

language = "English",

booktitle = "VCIP 2016 - 30th Anniversary of Visual Communication and Image Processing",

}

TY - GEN

T1 - Complex singular value decomposition based stereoscopic image quality assessment

AU - WANG, Xu

AU - CAO, Lei

AU - MA, Lin

AU - ZHOU, Yu

AU - KWONG, Sam

PY - 2016/11

Y1 - 2016/11

N2 - Designing a reliable and generic perceptual quality metric is a challenging issue in three-dimensional (3D) visual signal processing. Due to the limited knowledge on 3D perceptual, it is difficult to fuse the visual information of left and right views in an effective way. In this paper, we propose a complex singular value decomposition (CSVD) based stereoscopic image quality assessment (SIQA) metric. First, the corresponding blocks of the left/right view are grouped into complex representation (CR) block through the scale-invariant feature transform (SIFT) view matching process. Then we compute the CSVD coefficients of each CR block. Final, a CSVD based quality pooling stage is employed to predict the final visual quality of the distorted 3D image. Experimental results demonstrate that the proposed metric has good consistency with 3D perception of human.

AB - Designing a reliable and generic perceptual quality metric is a challenging issue in three-dimensional (3D) visual signal processing. Due to the limited knowledge on 3D perceptual, it is difficult to fuse the visual information of left and right views in an effective way. In this paper, we propose a complex singular value decomposition (CSVD) based stereoscopic image quality assessment (SIQA) metric. First, the corresponding blocks of the left/right view are grouped into complex representation (CR) block through the scale-invariant feature transform (SIFT) view matching process. Then we compute the CSVD coefficients of each CR block. Final, a CSVD based quality pooling stage is employed to predict the final visual quality of the distorted 3D image. Experimental results demonstrate that the proposed metric has good consistency with 3D perception of human.

KW - Complex Singular Value Decomposition

KW - Stereoscopic Image Quality Assessment

UR - http://www.scopus.com/inward/record.url?scp=85011024327&partnerID=8YFLogxK

U2 - 10.1109/VCIP.2016.7805497

DO - 10.1109/VCIP.2016.7805497

M3 - Conference paper (refereed)

BT - VCIP 2016 - 30th Anniversary of Visual Communication and Image Processing

ER -

Complex singular value decomposition based stereoscopic image quality assessment

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this