Synthesized texture quality assessment via multi-scale spatial and statistical texture attributes of image and gradient magnitude coefficients

S. Alireza Golestaneh, Lina Karam

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

Abstract

Perceptual quality assessment for synthesized textures is a challenging task. In this paper, we propose a trainingfree reduced-reference (RR) objective quality assessment method that quantifies the perceived quality of synthesized textures. The proposed reduced-reference synthesized texture quality assessment metric is based on measuring the spatial and statistical attributes of the texture image using both image-and gradient-based wavelet coefficients at multiple scales. Performance evaluations on two synthesized texture databases demonstrate that our proposed RR synthesized texture quality metric significantly outperforms both full-reference and RR state-of-the-art quality metrics in predicting the perceived visual quality of the synthesized textures.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
PublisherIEEE Computer Society
Pages851-857
Number of pages7
Volume2018-June
ISBN (Electronic)9781538661000
DOIs
StatePublished - Dec 13 2018
Event31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 - Salt Lake City, United States
Duration: Jun 18 2018Jun 22 2018

Other

Other31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
CountryUnited States
CitySalt Lake City
Period6/18/186/22/18

Fingerprint

Textures

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Golestaneh, S. A., & Karam, L. (2018). Synthesized texture quality assessment via multi-scale spatial and statistical texture attributes of image and gradient magnitude coefficients. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 (Vol. 2018-June, pp. 851-857). [8575268] IEEE Computer Society. https://doi.org/10.1109/CVPRW.2018.00117

Synthesized texture quality assessment via multi-scale spatial and statistical texture attributes of image and gradient magnitude coefficients. / Golestaneh, S. Alireza; Karam, Lina.

Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. Vol. 2018-June IEEE Computer Society, 2018. p. 851-857 8575268.

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

Golestaneh, SA & Karam, L 2018, Synthesized texture quality assessment via multi-scale spatial and statistical texture attributes of image and gradient magnitude coefficients. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. vol. 2018-June, 8575268, IEEE Computer Society, pp. 851-857, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018, Salt Lake City, United States, 6/18/18. https://doi.org/10.1109/CVPRW.2018.00117
Golestaneh SA, Karam L. Synthesized texture quality assessment via multi-scale spatial and statistical texture attributes of image and gradient magnitude coefficients. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. Vol. 2018-June. IEEE Computer Society. 2018. p. 851-857. 8575268 https://doi.org/10.1109/CVPRW.2018.00117
Golestaneh, S. Alireza ; Karam, Lina. / Synthesized texture quality assessment via multi-scale spatial and statistical texture attributes of image and gradient magnitude coefficients. Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. Vol. 2018-June IEEE Computer Society, 2018. pp. 851-857
@inproceedings{1c7f37323c5c461bab7271ed00b41ccb,
title = "Synthesized texture quality assessment via multi-scale spatial and statistical texture attributes of image and gradient magnitude coefficients",
abstract = "Perceptual quality assessment for synthesized textures is a challenging task. In this paper, we propose a trainingfree reduced-reference (RR) objective quality assessment method that quantifies the perceived quality of synthesized textures. The proposed reduced-reference synthesized texture quality assessment metric is based on measuring the spatial and statistical attributes of the texture image using both image-and gradient-based wavelet coefficients at multiple scales. Performance evaluations on two synthesized texture databases demonstrate that our proposed RR synthesized texture quality metric significantly outperforms both full-reference and RR state-of-the-art quality metrics in predicting the perceived visual quality of the synthesized textures.",
author = "Golestaneh, {S. Alireza} and Lina Karam",
year = "2018",
month = "12",
day = "13",
doi = "10.1109/CVPRW.2018.00117",
language = "English (US)",
volume = "2018-June",
pages = "851--857",
booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Synthesized texture quality assessment via multi-scale spatial and statistical texture attributes of image and gradient magnitude coefficients

AU - Golestaneh, S. Alireza

AU - Karam, Lina

PY - 2018/12/13

Y1 - 2018/12/13

N2 - Perceptual quality assessment for synthesized textures is a challenging task. In this paper, we propose a trainingfree reduced-reference (RR) objective quality assessment method that quantifies the perceived quality of synthesized textures. The proposed reduced-reference synthesized texture quality assessment metric is based on measuring the spatial and statistical attributes of the texture image using both image-and gradient-based wavelet coefficients at multiple scales. Performance evaluations on two synthesized texture databases demonstrate that our proposed RR synthesized texture quality metric significantly outperforms both full-reference and RR state-of-the-art quality metrics in predicting the perceived visual quality of the synthesized textures.

AB - Perceptual quality assessment for synthesized textures is a challenging task. In this paper, we propose a trainingfree reduced-reference (RR) objective quality assessment method that quantifies the perceived quality of synthesized textures. The proposed reduced-reference synthesized texture quality assessment metric is based on measuring the spatial and statistical attributes of the texture image using both image-and gradient-based wavelet coefficients at multiple scales. Performance evaluations on two synthesized texture databases demonstrate that our proposed RR synthesized texture quality metric significantly outperforms both full-reference and RR state-of-the-art quality metrics in predicting the perceived visual quality of the synthesized textures.

UR - http://www.scopus.com/inward/record.url?scp=85060859608&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060859608&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2018.00117

DO - 10.1109/CVPRW.2018.00117

M3 - Conference contribution

VL - 2018-June

SP - 851

EP - 857

BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018

PB - IEEE Computer Society

ER -