Assessing Perceived Image Quality Using Steady-State Visual Evoked Potentials and Spatio-Spectral Decomposition

Sebastian Bosse; Laura Acqualagna; Wojciech Samek; Anne K. Porbadnigk; Gabriel Curio; Benjamin Blankertz; Klaus Robert Müller; Thomas Wiegand

doi:10.1109/TCSVT.2017.2694807

Assessing Perceived Image Quality Using Steady-State Visual Evoked Potentials and Spatio-Spectral Decomposition

Sebastian Bosse, Laura Acqualagna, Wojciech Samek, Anne K. Porbadnigk, Gabriel Curio, Benjamin Blankertz, Klaus Robert Müller, Thomas Wiegand

Research output: Contribution to journal › Article › peer-review

20 Citations (Scopus)

Abstract

Steady-state visual evoked potentials (SSVEPs) are neural responses, measurable using electroencephalography (EEG), that are directly linked to sensory processing of visual stimuli. In this paper, SSVEP is used to assess the perceived quality of texture images. The EEG-based assessment method is compared with conventional methods, and recorded EEG data are correlated to obtained mean opinion scores (MOSs). A dimensionality reduction technique for EEG data called spatio-spectral decomposition (SSD) is adapted for the SSVEP framework and used to extract physiologically meaningful and plausible neural components from the EEG recordings. It is shown that the use of SSD not only increases the correlation between neural features and MOS to r=-0.93 , but also solves the problem of channel selection in an EEG-based image-quality assessment.

Original language	English
Article number	7902111
Pages (from-to)	1694-1706
Number of pages	13
Journal	IEEE Transactions on Circuits and Systems for Video Technology
Volume	28
Issue number	8
DOIs	https://doi.org/10.1109/TCSVT.2017.2694807
Publication status	Published - 2018 Aug

Keywords

EEG
MOS
SSVEP
classification
spatio-spectral decomposition
video quality assessment

ASJC Scopus subject areas

Media Technology
Electrical and Electronic Engineering

Access to Document

10.1109/TCSVT.2017.2694807

Cite this

@article{e5996199c71e4c18b072bad8b84fdbb8,

title = "Assessing Perceived Image Quality Using Steady-State Visual Evoked Potentials and Spatio-Spectral Decomposition",

abstract = "Steady-state visual evoked potentials (SSVEPs) are neural responses, measurable using electroencephalography (EEG), that are directly linked to sensory processing of visual stimuli. In this paper, SSVEP is used to assess the perceived quality of texture images. The EEG-based assessment method is compared with conventional methods, and recorded EEG data are correlated to obtained mean opinion scores (MOSs). A dimensionality reduction technique for EEG data called spatio-spectral decomposition (SSD) is adapted for the SSVEP framework and used to extract physiologically meaningful and plausible neural components from the EEG recordings. It is shown that the use of SSD not only increases the correlation between neural features and MOS to r=-0.93 , but also solves the problem of channel selection in an EEG-based image-quality assessment.",

keywords = "EEG, MOS, SSVEP, classification, spatio-spectral decomposition, video quality assessment",

author = "Sebastian Bosse and Laura Acqualagna and Wojciech Samek and Porbadnigk, {Anne K.} and Gabriel Curio and Benjamin Blankertz and M{\"u}ller, {Klaus Robert} and Thomas Wiegand",

note = "Funding Information: Manuscript received October 10, 2016; revised March 14, 2017; accepted April 6, 2017. Date of publication April 17, 2017; date of current version August 3, 2018. This work was supported by BMBF under Grant 01GQ0850. The work of K.-R. M{\"u}ller was supported by BK21 of NRF. This paper was recommended by Associate Editor P. Comesana-Alfaro. (Sebastian Bosse and Laura Acqualagna contributed equally to this work.) (Corresponding authors: Sebastian Bosse, Benjamin Blankertz, Klaus-Robert M{\"u}ller, and Thomas Wiegand.) S. Bosse and W. Samek are with the Video Coding and Analytics Department, Fraunhofer Heinrich Hertz Institute, 10587 Berlin, Germany (e-mail: sebastian.bosse@hhi.fraunhofer.de). Publisher Copyright: {\textcopyright} 1991-2012 IEEE.",

year = "2018",

month = aug,

doi = "10.1109/TCSVT.2017.2694807",

language = "English",

volume = "28",

pages = "1694--1706",

journal = "IEEE Transactions on Circuits and Systems for Video Technology",

issn = "1051-8215",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "8",

}

TY - JOUR

T1 - Assessing Perceived Image Quality Using Steady-State Visual Evoked Potentials and Spatio-Spectral Decomposition

AU - Bosse, Sebastian

AU - Acqualagna, Laura

AU - Samek, Wojciech

AU - Porbadnigk, Anne K.

AU - Curio, Gabriel

AU - Blankertz, Benjamin

AU - Müller, Klaus Robert

AU - Wiegand, Thomas

N1 - Funding Information: Manuscript received October 10, 2016; revised March 14, 2017; accepted April 6, 2017. Date of publication April 17, 2017; date of current version August 3, 2018. This work was supported by BMBF under Grant 01GQ0850. The work of K.-R. Müller was supported by BK21 of NRF. This paper was recommended by Associate Editor P. Comesana-Alfaro. (Sebastian Bosse and Laura Acqualagna contributed equally to this work.) (Corresponding authors: Sebastian Bosse, Benjamin Blankertz, Klaus-Robert Müller, and Thomas Wiegand.) S. Bosse and W. Samek are with the Video Coding and Analytics Department, Fraunhofer Heinrich Hertz Institute, 10587 Berlin, Germany (e-mail: sebastian.bosse@hhi.fraunhofer.de). Publisher Copyright: © 1991-2012 IEEE.

PY - 2018/8

Y1 - 2018/8

N2 - Steady-state visual evoked potentials (SSVEPs) are neural responses, measurable using electroencephalography (EEG), that are directly linked to sensory processing of visual stimuli. In this paper, SSVEP is used to assess the perceived quality of texture images. The EEG-based assessment method is compared with conventional methods, and recorded EEG data are correlated to obtained mean opinion scores (MOSs). A dimensionality reduction technique for EEG data called spatio-spectral decomposition (SSD) is adapted for the SSVEP framework and used to extract physiologically meaningful and plausible neural components from the EEG recordings. It is shown that the use of SSD not only increases the correlation between neural features and MOS to r=-0.93 , but also solves the problem of channel selection in an EEG-based image-quality assessment.

AB - Steady-state visual evoked potentials (SSVEPs) are neural responses, measurable using electroencephalography (EEG), that are directly linked to sensory processing of visual stimuli. In this paper, SSVEP is used to assess the perceived quality of texture images. The EEG-based assessment method is compared with conventional methods, and recorded EEG data are correlated to obtained mean opinion scores (MOSs). A dimensionality reduction technique for EEG data called spatio-spectral decomposition (SSD) is adapted for the SSVEP framework and used to extract physiologically meaningful and plausible neural components from the EEG recordings. It is shown that the use of SSD not only increases the correlation between neural features and MOS to r=-0.93 , but also solves the problem of channel selection in an EEG-based image-quality assessment.

KW - EEG

KW - MOS

KW - SSVEP

KW - classification

KW - spatio-spectral decomposition

KW - video quality assessment

UR - http://www.scopus.com/inward/record.url?scp=85038229055&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2017.2694807

DO - 10.1109/TCSVT.2017.2694807

M3 - Article

AN - SCOPUS:85038229055

VL - 28

SP - 1694

EP - 1706

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 8

M1 - 7902111

ER -

Assessing Perceived Image Quality Using Steady-State Visual Evoked Potentials and Spatio-Spectral Decomposition

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this