Objective no-reference stereoscopic image quality prediction based on 2d image features and relative disparity

Z. M.Parvez Sazzad, Roushain Akhter, J. Baltes, Y. Horita

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

Stereoscopic images are widely used to enhance the viewing experience of three-dimensional (3D) imaging and communication system. In this paper, we propose an image feature and disparity dependent quality evaluation metric, which incorporates human visible system characteristics. We believe perceived distortions and disparity of any stereoscopic image are strongly dependent on local features, such as edge (i.e., nonplane areas of an image) and nonedge (i.e., plane areas of an image) areas within the image. Therefore, a no-reference perceptual quality assessment method is developed for JPEG coded stereoscopic images based on segmented local features of distortions and disparity. Local feature information such as edge and non-edge area based relative disparity estimation, as well as the blockiness and the edge distortion within the block of images are evaluated in this method. Subjective stereo image database is used for evaluation of the metric. The subjective experiment results indicate that our metric has sufficient prediction performance.

Original languageEnglish
Article number256130
JournalAdvances in Multimedia
Volume2012
DOIs
Publication statusPublished - 2012 Aug 17

Fingerprint

Image quality
Imaging systems
Communication systems
Experiments

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Objective no-reference stereoscopic image quality prediction based on 2d image features and relative disparity. / Sazzad, Z. M.Parvez; Akhter, Roushain; Baltes, J.; Horita, Y.

In: Advances in Multimedia, Vol. 2012, 256130, 17.08.2012.

Research output: Contribution to journalArticle

@article{8cb712f00c934e48884c9fb4080bfcb2,
title = "Objective no-reference stereoscopic image quality prediction based on 2d image features and relative disparity",
abstract = "Stereoscopic images are widely used to enhance the viewing experience of three-dimensional (3D) imaging and communication system. In this paper, we propose an image feature and disparity dependent quality evaluation metric, which incorporates human visible system characteristics. We believe perceived distortions and disparity of any stereoscopic image are strongly dependent on local features, such as edge (i.e., nonplane areas of an image) and nonedge (i.e., plane areas of an image) areas within the image. Therefore, a no-reference perceptual quality assessment method is developed for JPEG coded stereoscopic images based on segmented local features of distortions and disparity. Local feature information such as edge and non-edge area based relative disparity estimation, as well as the blockiness and the edge distortion within the block of images are evaluated in this method. Subjective stereo image database is used for evaluation of the metric. The subjective experiment results indicate that our metric has sufficient prediction performance.",
author = "Sazzad, {Z. M.Parvez} and Roushain Akhter and J. Baltes and Y. Horita",
year = "2012",
month = "8",
day = "17",
doi = "10.1155/2012/256130",
language = "English",
volume = "2012",
journal = "Advances in Multimedia",
issn = "1687-5680",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Objective no-reference stereoscopic image quality prediction based on 2d image features and relative disparity

AU - Sazzad, Z. M.Parvez

AU - Akhter, Roushain

AU - Baltes, J.

AU - Horita, Y.

PY - 2012/8/17

Y1 - 2012/8/17

N2 - Stereoscopic images are widely used to enhance the viewing experience of three-dimensional (3D) imaging and communication system. In this paper, we propose an image feature and disparity dependent quality evaluation metric, which incorporates human visible system characteristics. We believe perceived distortions and disparity of any stereoscopic image are strongly dependent on local features, such as edge (i.e., nonplane areas of an image) and nonedge (i.e., plane areas of an image) areas within the image. Therefore, a no-reference perceptual quality assessment method is developed for JPEG coded stereoscopic images based on segmented local features of distortions and disparity. Local feature information such as edge and non-edge area based relative disparity estimation, as well as the blockiness and the edge distortion within the block of images are evaluated in this method. Subjective stereo image database is used for evaluation of the metric. The subjective experiment results indicate that our metric has sufficient prediction performance.

AB - Stereoscopic images are widely used to enhance the viewing experience of three-dimensional (3D) imaging and communication system. In this paper, we propose an image feature and disparity dependent quality evaluation metric, which incorporates human visible system characteristics. We believe perceived distortions and disparity of any stereoscopic image are strongly dependent on local features, such as edge (i.e., nonplane areas of an image) and nonedge (i.e., plane areas of an image) areas within the image. Therefore, a no-reference perceptual quality assessment method is developed for JPEG coded stereoscopic images based on segmented local features of distortions and disparity. Local feature information such as edge and non-edge area based relative disparity estimation, as well as the blockiness and the edge distortion within the block of images are evaluated in this method. Subjective stereo image database is used for evaluation of the metric. The subjective experiment results indicate that our metric has sufficient prediction performance.

UR - http://www.scopus.com/inward/record.url?scp=84864921144&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864921144&partnerID=8YFLogxK

U2 - 10.1155/2012/256130

DO - 10.1155/2012/256130

M3 - Article

AN - SCOPUS:84864921144

VL - 2012

JO - Advances in Multimedia

JF - Advances in Multimedia

SN - 1687-5680

M1 - 256130

ER -