A Study of Stereoscopic Image Quality Assessment Model Corresponding to Disparate Quality of Left/Right Image for JPEG Coding

Masaharu SATO; Yuukou HORITA

doi:10.1587/transfun.E95.A.1264

A Study of Stereoscopic Image Quality Assessment Model Corresponding to Disparate Quality of Left/Right Image for JPEG Coding

Masaharu SATO, Yuukou HORITA

Full Text Views

0

Share
Cite this

Summary :

Our research is focused on examining a stereoscopic quality assessment model for stereoscopic images with disparate quality in left and right images for glasses-free stereo vision. In this paper, we examine the objective assessment model of 3-D images, considering the difference in image quality between each view-point generated by the disparity-compensated coding. A overall stereoscopic image quality can be estimated by using only predicted values of left and right 2-D image qualities based on the MPEG-7 descriptor information without using any disparity information. As a result, the stereoscopic still image quality is assessed with high prediction accuracy with correlation coefficient=0.98 and average error=0.17.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E95-A No.8 pp.1264-1269

Publication Date: 2012/08/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E95.A.1264

Type of Manuscript: Special Section LETTER (Special Section on Image Media Quality)

Category: Quality Metrics

Cite this

Copy

Masaharu SATO, Yuukou HORITA, "A Study of Stereoscopic Image Quality Assessment Model Corresponding to Disparate Quality of Left/Right Image for JPEG Coding" in IEICE TRANSACTIONS on Fundamentals, vol. E95-A, no. 8, pp. 1264-1269, August 2012, doi: 10.1587/transfun.E95.A.1264.
Abstract: Our research is focused on examining a stereoscopic quality assessment model for stereoscopic images with disparate quality in left and right images for glasses-free stereo vision. In this paper, we examine the objective assessment model of 3-D images, considering the difference in image quality between each view-point generated by the disparity-compensated coding. A overall stereoscopic image quality can be estimated by using only predicted values of left and right 2-D image qualities based on the MPEG-7 descriptor information without using any disparity information. As a result, the stereoscopic still image quality is assessed with high prediction accuracy with correlation coefficient=0.98 and average error=0.17.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/transfun.E95.A.1264/_p

Copy

@ARTICLE{e95-a_8_1264,
author={Masaharu SATO, Yuukou HORITA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Study of Stereoscopic Image Quality Assessment Model Corresponding to Disparate Quality of Left/Right Image for JPEG Coding},
year={2012},
volume={E95-A},
number={8},
pages={1264-1269},
abstract={Our research is focused on examining a stereoscopic quality assessment model for stereoscopic images with disparate quality in left and right images for glasses-free stereo vision. In this paper, we examine the objective assessment model of 3-D images, considering the difference in image quality between each view-point generated by the disparity-compensated coding. A overall stereoscopic image quality can be estimated by using only predicted values of left and right 2-D image qualities based on the MPEG-7 descriptor information without using any disparity information. As a result, the stereoscopic still image quality is assessed with high prediction accuracy with correlation coefficient=0.98 and average error=0.17.},
keywords={},
doi={10.1587/transfun.E95.A.1264},
ISSN={1745-1337},
month={August},}

Copy

TY - JOUR
TI - A Study of Stereoscopic Image Quality Assessment Model Corresponding to Disparate Quality of Left/Right Image for JPEG Coding
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1264
EP - 1269
AU - Masaharu SATO
AU - Yuukou HORITA
PY - 2012
DO - 10.1587/transfun.E95.A.1264
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E95-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 2012
AB - Our research is focused on examining a stereoscopic quality assessment model for stereoscopic images with disparate quality in left and right images for glasses-free stereo vision. In this paper, we examine the objective assessment model of 3-D images, considering the difference in image quality between each view-point generated by the disparity-compensated coding. A overall stereoscopic image quality can be estimated by using only predicted values of left and right 2-D image qualities based on the MPEG-7 descriptor information without using any disparity information. As a result, the stereoscopic still image quality is assessed with high prediction accuracy with correlation coefficient=0.98 and average error=0.17.
ER -