No-reference stereoscopic image quality assessment

Roushain Akhter, Z. M. Parvez Sazzad, Y. Horita, Hansjoerg (Jacky) Baltes

Research output: Chapter in Book/Report/Conference proceedingConference contribution

93 Citations (Scopus)

Abstract

Display of stereo images is widely used to enhance the viewing experience of three-dimensional imaging and communication systems. In this paper, we propose a method for estimating the quality of stereoscopic images using segmented image features and disparity. This method is inspired by the human visual system. We believe the perceived distortion and disparity of any stereoscopic display is strongly dependent on local features, such as edge (non-plane) and non-edge (plane) areas. Therefore, a no-reference perceptual quality assessment is developed for JPEG coded stereoscopic images based on segmented local features of artifacts and disparity. Local feature information such as edge and non-edge area based relative disparity estimation, as well as the blockiness and the blur within the block of images are evaluated in this method. Two subjective stereo image databases are used to evaluate the performance of our method. The subjective experiments results indicate our model has sufficient prediction performance.

Original languageEnglish
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Stereoscopic Displays and Applications XXI
DOIs
Publication statusPublished - 2010 Mar 25
EventStereoscopic Displays and Applications XXI - San Jose, CA, United States
Duration: 2010 Jan 182010 Jan 20

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume7524
ISSN (Print)0277-786X

Other

OtherStereoscopic Displays and Applications XXI
CountryUnited States
CitySan Jose, CA
Period10/1/1810/1/20

Fingerprint

Image Quality Assessment
Image quality
Display devices
Local Features
Imaging systems
Communication systems
Stereoscopic Display
Three-dimensional Imaging
Human Visual System
Quality Assessment
Image Database
Performance Prediction
performance prediction
Imaging System
Experiments
Communication Systems
Display
artifacts
telecommunication
Sufficient

Keywords

  • Auto stereoscopic display
  • Disparity
  • JPEG
  • No-reference
  • Segmentation

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Akhter, R., Parvez Sazzad, Z. M., Horita, Y., & Baltes, H. J. (2010). No-reference stereoscopic image quality assessment. In Proceedings of SPIE-IS and T Electronic Imaging - Stereoscopic Displays and Applications XXI [75240T] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7524). https://doi.org/10.1117/12.838775

No-reference stereoscopic image quality assessment. / Akhter, Roushain; Parvez Sazzad, Z. M.; Horita, Y.; Baltes, Hansjoerg (Jacky).

Proceedings of SPIE-IS and T Electronic Imaging - Stereoscopic Displays and Applications XXI. 2010. 75240T (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7524).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Akhter, R, Parvez Sazzad, ZM, Horita, Y & Baltes, HJ 2010, No-reference stereoscopic image quality assessment. in Proceedings of SPIE-IS and T Electronic Imaging - Stereoscopic Displays and Applications XXI., 75240T, Proceedings of SPIE - The International Society for Optical Engineering, vol. 7524, Stereoscopic Displays and Applications XXI, San Jose, CA, United States, 10/1/18. https://doi.org/10.1117/12.838775
Akhter R, Parvez Sazzad ZM, Horita Y, Baltes HJ. No-reference stereoscopic image quality assessment. In Proceedings of SPIE-IS and T Electronic Imaging - Stereoscopic Displays and Applications XXI. 2010. 75240T. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.838775
Akhter, Roushain ; Parvez Sazzad, Z. M. ; Horita, Y. ; Baltes, Hansjoerg (Jacky). / No-reference stereoscopic image quality assessment. Proceedings of SPIE-IS and T Electronic Imaging - Stereoscopic Displays and Applications XXI. 2010. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{7fca35a73ec74d22b3b1d982fc475804,
title = "No-reference stereoscopic image quality assessment",
abstract = "Display of stereo images is widely used to enhance the viewing experience of three-dimensional imaging and communication systems. In this paper, we propose a method for estimating the quality of stereoscopic images using segmented image features and disparity. This method is inspired by the human visual system. We believe the perceived distortion and disparity of any stereoscopic display is strongly dependent on local features, such as edge (non-plane) and non-edge (plane) areas. Therefore, a no-reference perceptual quality assessment is developed for JPEG coded stereoscopic images based on segmented local features of artifacts and disparity. Local feature information such as edge and non-edge area based relative disparity estimation, as well as the blockiness and the blur within the block of images are evaluated in this method. Two subjective stereo image databases are used to evaluate the performance of our method. The subjective experiments results indicate our model has sufficient prediction performance.",
keywords = "Auto stereoscopic display, Disparity, JPEG, No-reference, Segmentation",
author = "Roushain Akhter and {Parvez Sazzad}, {Z. M.} and Y. Horita and Baltes, {Hansjoerg (Jacky)}",
year = "2010",
month = "3",
day = "25",
doi = "10.1117/12.838775",
language = "English",
isbn = "9780819479174",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Proceedings of SPIE-IS and T Electronic Imaging - Stereoscopic Displays and Applications XXI",

}

TY - GEN

T1 - No-reference stereoscopic image quality assessment

AU - Akhter, Roushain

AU - Parvez Sazzad, Z. M.

AU - Horita, Y.

AU - Baltes, Hansjoerg (Jacky)

PY - 2010/3/25

Y1 - 2010/3/25

N2 - Display of stereo images is widely used to enhance the viewing experience of three-dimensional imaging and communication systems. In this paper, we propose a method for estimating the quality of stereoscopic images using segmented image features and disparity. This method is inspired by the human visual system. We believe the perceived distortion and disparity of any stereoscopic display is strongly dependent on local features, such as edge (non-plane) and non-edge (plane) areas. Therefore, a no-reference perceptual quality assessment is developed for JPEG coded stereoscopic images based on segmented local features of artifacts and disparity. Local feature information such as edge and non-edge area based relative disparity estimation, as well as the blockiness and the blur within the block of images are evaluated in this method. Two subjective stereo image databases are used to evaluate the performance of our method. The subjective experiments results indicate our model has sufficient prediction performance.

AB - Display of stereo images is widely used to enhance the viewing experience of three-dimensional imaging and communication systems. In this paper, we propose a method for estimating the quality of stereoscopic images using segmented image features and disparity. This method is inspired by the human visual system. We believe the perceived distortion and disparity of any stereoscopic display is strongly dependent on local features, such as edge (non-plane) and non-edge (plane) areas. Therefore, a no-reference perceptual quality assessment is developed for JPEG coded stereoscopic images based on segmented local features of artifacts and disparity. Local feature information such as edge and non-edge area based relative disparity estimation, as well as the blockiness and the blur within the block of images are evaluated in this method. Two subjective stereo image databases are used to evaluate the performance of our method. The subjective experiments results indicate our model has sufficient prediction performance.

KW - Auto stereoscopic display

KW - Disparity

KW - JPEG

KW - No-reference

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=77949622791&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949622791&partnerID=8YFLogxK

U2 - 10.1117/12.838775

DO - 10.1117/12.838775

M3 - Conference contribution

AN - SCOPUS:77949622791

SN - 9780819479174

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Proceedings of SPIE-IS and T Electronic Imaging - Stereoscopic Displays and Applications XXI

ER -