Neurally informed assessment of perceived natural texture image quality

Sebastian Bosse; Laura Acqualagna; Anne K. Porbadnigk; Benjamin Blankertz; Gabriel Curio; Klaus Muller; Thomas Wiegand

doi:10.1109/ICIP.2014.7025398

Neurally informed assessment of perceived natural texture image quality

Sebastian Bosse, Laura Acqualagna, Anne K. Porbadnigk, Benjamin Blankertz, Gabriel Curio, Klaus Muller, Thomas Wiegand

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

20 Citations (Scopus)

Abstract

Conventionally, the quality of images and related codecs are assessed using subjective tests, such as Degradation Category Rating. These quality assessments consider the behavioral level only. Recently, it has been proposed to complement this approach by investigating how quality is processed in the brain of a user (using electroencephalography, EEG), potentially leading to results that are less biased by subjective factors. In this paper, a novel method is presented for assessing how image quality is processed on a neural level, using Steady-State Visual Evoked Potentials (SSVEPs) as EEG features. We tested our approach in an EEG study with 16 participants who were presented with distorted images of natural textures. Subsequently, we compared our approach analogously to the standardized Degradation Category Rating quality assessment. Remarkably, our novel method yields a correlation of r = 0.93 to MOS on the recorded dataset.

Original language	English
Title of host publication	2014 IEEE International Conference on Image Processing, ICIP 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1987-1991
Number of pages	5
ISBN (Print)	9781479957514
DOIs	https://doi.org/10.1109/ICIP.2014.7025398
Publication status	Published - 2015 Jan 28
Externally published	Yes
Event	2014 IEEE International Conference on Image Processing, ICIP 2014 - Paris, France Duration: 2014 Oct 27 → 2014 Oct 30

Other

Other	2014 IEEE International Conference on Image Processing, ICIP 2014
Country/Territory	France
City	Paris
Period	14/10/27 → 14/10/30

Keywords

EEG
image coding
Image quality
perception electroencephalography

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICIP.2014.7025398

Cite this

Bosse, S., Acqualagna, L., Porbadnigk, A. K., Blankertz, B., Curio, G., Muller, K., & Wiegand, T. (2015). Neurally informed assessment of perceived natural texture image quality. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 1987-1991). Article 7025398 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7025398

Neurally informed assessment of perceived natural texture image quality. / Bosse, Sebastian; Acqualagna, Laura; Porbadnigk, Anne K. et al.
2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1987-1991 7025398.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Bosse, S, Acqualagna, L, Porbadnigk, AK, Blankertz, B, Curio, G, Muller, K & Wiegand, T 2015, Neurally informed assessment of perceived natural texture image quality. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7025398, Institute of Electrical and Electronics Engineers Inc., pp. 1987-1991, 2014 IEEE International Conference on Image Processing, ICIP 2014, Paris, France, 14/10/27. https://doi.org/10.1109/ICIP.2014.7025398

@inproceedings{41a6a571bc594ad1890b43500b5f3862,

title = "Neurally informed assessment of perceived natural texture image quality",

abstract = "Conventionally, the quality of images and related codecs are assessed using subjective tests, such as Degradation Category Rating. These quality assessments consider the behavioral level only. Recently, it has been proposed to complement this approach by investigating how quality is processed in the brain of a user (using electroencephalography, EEG), potentially leading to results that are less biased by subjective factors. In this paper, a novel method is presented for assessing how image quality is processed on a neural level, using Steady-State Visual Evoked Potentials (SSVEPs) as EEG features. We tested our approach in an EEG study with 16 participants who were presented with distorted images of natural textures. Subsequently, we compared our approach analogously to the standardized Degradation Category Rating quality assessment. Remarkably, our novel method yields a correlation of r = 0.93 to MOS on the recorded dataset.",

keywords = "EEG, image coding, Image quality, perception electroencephalography",

author = "Sebastian Bosse and Laura Acqualagna and Porbadnigk, {Anne K.} and Benjamin Blankertz and Gabriel Curio and Klaus Muller and Thomas Wiegand",

year = "2015",

month = jan,

day = "28",

doi = "10.1109/ICIP.2014.7025398",

language = "English",

isbn = "9781479957514",

pages = "1987--1991",

booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",

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

note = "2014 IEEE International Conference on Image Processing, ICIP 2014 ; Conference date: 27-10-2014 Through 30-10-2014",

}

TY - GEN

T1 - Neurally informed assessment of perceived natural texture image quality

AU - Bosse, Sebastian

AU - Acqualagna, Laura

AU - Porbadnigk, Anne K.

AU - Blankertz, Benjamin

AU - Curio, Gabriel

AU - Muller, Klaus

AU - Wiegand, Thomas

PY - 2015/1/28

Y1 - 2015/1/28

N2 - Conventionally, the quality of images and related codecs are assessed using subjective tests, such as Degradation Category Rating. These quality assessments consider the behavioral level only. Recently, it has been proposed to complement this approach by investigating how quality is processed in the brain of a user (using electroencephalography, EEG), potentially leading to results that are less biased by subjective factors. In this paper, a novel method is presented for assessing how image quality is processed on a neural level, using Steady-State Visual Evoked Potentials (SSVEPs) as EEG features. We tested our approach in an EEG study with 16 participants who were presented with distorted images of natural textures. Subsequently, we compared our approach analogously to the standardized Degradation Category Rating quality assessment. Remarkably, our novel method yields a correlation of r = 0.93 to MOS on the recorded dataset.

AB - Conventionally, the quality of images and related codecs are assessed using subjective tests, such as Degradation Category Rating. These quality assessments consider the behavioral level only. Recently, it has been proposed to complement this approach by investigating how quality is processed in the brain of a user (using electroencephalography, EEG), potentially leading to results that are less biased by subjective factors. In this paper, a novel method is presented for assessing how image quality is processed on a neural level, using Steady-State Visual Evoked Potentials (SSVEPs) as EEG features. We tested our approach in an EEG study with 16 participants who were presented with distorted images of natural textures. Subsequently, we compared our approach analogously to the standardized Degradation Category Rating quality assessment. Remarkably, our novel method yields a correlation of r = 0.93 to MOS on the recorded dataset.

KW - EEG

KW - image coding

KW - Image quality

KW - perception electroencephalography

UR - http://www.scopus.com/inward/record.url?scp=84931046977&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84931046977&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7025398

DO - 10.1109/ICIP.2014.7025398

M3 - Conference contribution

AN - SCOPUS:84924885520

SN - 9781479957514

SP - 1987

EP - 1991

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE International Conference on Image Processing, ICIP 2014

Y2 - 27 October 2014 through 30 October 2014

ER -

Neurally informed assessment of perceived natural texture image quality

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this