Reduced-reference synthesized-texture quality assessment based on multi-scale spatial and statistical texture attributes

S. Alireza Golestaneh, Lina Karam

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

3 Citations (Scopus)

Abstract

In this paper, we propose a reduced-reference (RR) objective quality assessment method that quantifies the perceived quality of synthesized textures. The proposed metric is based on measuring the granularity, regularity, and statistical attributes of the texture image. Furthermore, the proposed RR metric exhibits a significantly low overhead as compared to existing RR metrics by only requiring the transmission of 7 parameters as side information. Performance evaluations on two synthesized texture databases demonstrate that the proposed RR metric outperforms both full-reference (FR) and RR state-of-the-art quality metrics in predicting the perceived visual quality of the synthesized textures.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PublisherIEEE Computer Society
Pages3783-3786
Number of pages4
Volume2016-August
ISBN (Electronic)9781467399616
DOIs
StatePublished - Aug 3 2016
Event23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States
Duration: Sep 25 2016Sep 28 2016

Other

Other23rd IEEE International Conference on Image Processing, ICIP 2016
CountryUnited States
CityPhoenix
Period9/25/169/28/16

Fingerprint

Textures

Keywords

  • Granularity
  • Reduced-reference quality assessment
  • Regularity
  • Texture quality assessment

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Golestaneh, S. A., & Karam, L. (2016). Reduced-reference synthesized-texture quality assessment based on multi-scale spatial and statistical texture attributes. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings (Vol. 2016-August, pp. 3783-3786). [7533067] IEEE Computer Society. https://doi.org/10.1109/ICIP.2016.7533067

Reduced-reference synthesized-texture quality assessment based on multi-scale spatial and statistical texture attributes. / Golestaneh, S. Alireza; Karam, Lina.

2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. p. 3783-3786 7533067.

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

Golestaneh, SA & Karam, L 2016, Reduced-reference synthesized-texture quality assessment based on multi-scale spatial and statistical texture attributes. in 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. vol. 2016-August, 7533067, IEEE Computer Society, pp. 3783-3786, 23rd IEEE International Conference on Image Processing, ICIP 2016, Phoenix, United States, 9/25/16. https://doi.org/10.1109/ICIP.2016.7533067
Golestaneh SA, Karam L. Reduced-reference synthesized-texture quality assessment based on multi-scale spatial and statistical texture attributes. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August. IEEE Computer Society. 2016. p. 3783-3786. 7533067 https://doi.org/10.1109/ICIP.2016.7533067
Golestaneh, S. Alireza ; Karam, Lina. / Reduced-reference synthesized-texture quality assessment based on multi-scale spatial and statistical texture attributes. 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. pp. 3783-3786
@inproceedings{d120955ed47d415c957ba21a4c395bd7,
title = "Reduced-reference synthesized-texture quality assessment based on multi-scale spatial and statistical texture attributes",
abstract = "In this paper, we propose a reduced-reference (RR) objective quality assessment method that quantifies the perceived quality of synthesized textures. The proposed metric is based on measuring the granularity, regularity, and statistical attributes of the texture image. Furthermore, the proposed RR metric exhibits a significantly low overhead as compared to existing RR metrics by only requiring the transmission of 7 parameters as side information. Performance evaluations on two synthesized texture databases demonstrate that the proposed RR metric outperforms both full-reference (FR) and RR state-of-the-art quality metrics in predicting the perceived visual quality of the synthesized textures.",
keywords = "Granularity, Reduced-reference quality assessment, Regularity, Texture quality assessment",
author = "Golestaneh, {S. Alireza} and Lina Karam",
year = "2016",
month = "8",
day = "3",
doi = "10.1109/ICIP.2016.7533067",
language = "English (US)",
volume = "2016-August",
pages = "3783--3786",
booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Reduced-reference synthesized-texture quality assessment based on multi-scale spatial and statistical texture attributes

AU - Golestaneh, S. Alireza

AU - Karam, Lina

PY - 2016/8/3

Y1 - 2016/8/3

N2 - In this paper, we propose a reduced-reference (RR) objective quality assessment method that quantifies the perceived quality of synthesized textures. The proposed metric is based on measuring the granularity, regularity, and statistical attributes of the texture image. Furthermore, the proposed RR metric exhibits a significantly low overhead as compared to existing RR metrics by only requiring the transmission of 7 parameters as side information. Performance evaluations on two synthesized texture databases demonstrate that the proposed RR metric outperforms both full-reference (FR) and RR state-of-the-art quality metrics in predicting the perceived visual quality of the synthesized textures.

AB - In this paper, we propose a reduced-reference (RR) objective quality assessment method that quantifies the perceived quality of synthesized textures. The proposed metric is based on measuring the granularity, regularity, and statistical attributes of the texture image. Furthermore, the proposed RR metric exhibits a significantly low overhead as compared to existing RR metrics by only requiring the transmission of 7 parameters as side information. Performance evaluations on two synthesized texture databases demonstrate that the proposed RR metric outperforms both full-reference (FR) and RR state-of-the-art quality metrics in predicting the perceived visual quality of the synthesized textures.

KW - Granularity

KW - Reduced-reference quality assessment

KW - Regularity

KW - Texture quality assessment

UR - http://www.scopus.com/inward/record.url?scp=85006817944&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006817944&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2016.7533067

DO - 10.1109/ICIP.2016.7533067

M3 - Conference contribution

AN - SCOPUS:85006817944

VL - 2016-August

SP - 3783

EP - 3786

BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings

PB - IEEE Computer Society

ER -