Local binary pattern statistics feature for reduced reference image quality assessment

Min Zhang; Xuanqin Mou; Hiroshi Fujita; Lei Zhang; Xiangrong Zhou; Wufeng Xue

doi:10.1117/12.2008646

Local binary pattern statistics feature for reduced reference image quality assessment

Min Zhang, Xuanqin Mou, Hiroshi Fujita, Lei Zhang, Xiangrong Zhou, Wufeng Xue

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

7 Citations (Scopus)

Abstract

Measurement of visual quality is of fundamental importance for numerous image and video processing applications. This paper presented a novel and concise reduced reference (RR) image quality assessment method. Statistics of local binary pattern (LBP) is introduced as a similarity measure to form a novel RR image quality assessment (IQA) method for the first time. With this method, first, the test image is decomposed with a multi-scale transform. Second, LBP encoding maps are extracted for each of subband images. Third, the histograms are extracted from the LBP encoding map to form the RR features. In this way, image structure primitive information for RR features extraction can be reduced greatly. Hence, new RR IQA method is formed with only at most 56 RR features. The experimental results on two large scale IQA databases show that the statistic of LBPs is fairly robust and reliable to RR IQA task. The proposed methods show strong correlations with subjective quality evaluations.

Original language	English
Title of host publication	Proceedings of SPIE-IS and T Electronic Imaging - Digital Photography IX
DOIs	https://doi.org/10.1117/12.2008646
Publication status	Published - 11 Apr 2013
Event	Digital Photography IX - Burlingame, CA, United States Duration: 4 Feb 2013 → 6 Feb 2013

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	8660
ISSN (Print)	0277-786X

Conference

Conference	Digital Photography IX
Country	United States
City	Burlingame, CA
Period	4/02/13 → 6/02/13

Keywords

Image quality assessment (IQA)
local binary pattern
reduced reference

ASJC Scopus subject areas

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

More information

10.1117/12.2008646

Link to publication in Scopus

Cite this

@inproceedings{d6a4a6a3284b45bf9bee20093e7af68f,

title = "Local binary pattern statistics feature for reduced reference image quality assessment",

abstract = "Measurement of visual quality is of fundamental importance for numerous image and video processing applications. This paper presented a novel and concise reduced reference (RR) image quality assessment method. Statistics of local binary pattern (LBP) is introduced as a similarity measure to form a novel RR image quality assessment (IQA) method for the first time. With this method, first, the test image is decomposed with a multi-scale transform. Second, LBP encoding maps are extracted for each of subband images. Third, the histograms are extracted from the LBP encoding map to form the RR features. In this way, image structure primitive information for RR features extraction can be reduced greatly. Hence, new RR IQA method is formed with only at most 56 RR features. The experimental results on two large scale IQA databases show that the statistic of LBPs is fairly robust and reliable to RR IQA task. The proposed methods show strong correlations with subjective quality evaluations.",

keywords = "Image quality assessment (IQA), local binary pattern, reduced reference",

author = "Min Zhang and Xuanqin Mou and Hiroshi Fujita and Lei Zhang and Xiangrong Zhou and Wufeng Xue",

year = "2013",

month = apr,

day = "11",

doi = "10.1117/12.2008646",

language = "English",

isbn = "9780819494337",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

booktitle = "Proceedings of SPIE-IS and T Electronic Imaging - Digital Photography IX",

note = "Digital Photography IX ; Conference date: 04-02-2013 Through 06-02-2013",

}

Zhang, M, Mou, X, Fujita, H, Zhang, L, Zhou, X & Xue, W 2013, Local binary pattern statistics feature for reduced reference image quality assessment. in Proceedings of SPIE-IS and T Electronic Imaging - Digital Photography IX., 86600L, Proceedings of SPIE - The International Society for Optical Engineering, vol. 8660, Digital Photography IX, Burlingame, CA, United States, 4/02/13. https://doi.org/10.1117/12.2008646

Local binary pattern statistics feature for reduced reference image quality assessment. / Zhang, Min; Mou, Xuanqin; Fujita, Hiroshi; Zhang, Lei; Zhou, Xiangrong; Xue, Wufeng.

Proceedings of SPIE-IS and T Electronic Imaging - Digital Photography IX. 2013. 86600L (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8660).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Local binary pattern statistics feature for reduced reference image quality assessment

AU - Zhang, Min

AU - Mou, Xuanqin

AU - Fujita, Hiroshi

AU - Zhang, Lei

AU - Zhou, Xiangrong

AU - Xue, Wufeng

PY - 2013/4/11

Y1 - 2013/4/11

N2 - Measurement of visual quality is of fundamental importance for numerous image and video processing applications. This paper presented a novel and concise reduced reference (RR) image quality assessment method. Statistics of local binary pattern (LBP) is introduced as a similarity measure to form a novel RR image quality assessment (IQA) method for the first time. With this method, first, the test image is decomposed with a multi-scale transform. Second, LBP encoding maps are extracted for each of subband images. Third, the histograms are extracted from the LBP encoding map to form the RR features. In this way, image structure primitive information for RR features extraction can be reduced greatly. Hence, new RR IQA method is formed with only at most 56 RR features. The experimental results on two large scale IQA databases show that the statistic of LBPs is fairly robust and reliable to RR IQA task. The proposed methods show strong correlations with subjective quality evaluations.

AB - Measurement of visual quality is of fundamental importance for numerous image and video processing applications. This paper presented a novel and concise reduced reference (RR) image quality assessment method. Statistics of local binary pattern (LBP) is introduced as a similarity measure to form a novel RR image quality assessment (IQA) method for the first time. With this method, first, the test image is decomposed with a multi-scale transform. Second, LBP encoding maps are extracted for each of subband images. Third, the histograms are extracted from the LBP encoding map to form the RR features. In this way, image structure primitive information for RR features extraction can be reduced greatly. Hence, new RR IQA method is formed with only at most 56 RR features. The experimental results on two large scale IQA databases show that the statistic of LBPs is fairly robust and reliable to RR IQA task. The proposed methods show strong correlations with subjective quality evaluations.

KW - Image quality assessment (IQA)

KW - local binary pattern

KW - reduced reference

UR - http://www.scopus.com/inward/record.url?scp=84875881472&partnerID=8YFLogxK

U2 - 10.1117/12.2008646

DO - 10.1117/12.2008646

M3 - Conference article published in proceeding or book

AN - SCOPUS:84875881472

SN - 9780819494337

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

BT - Proceedings of SPIE-IS and T Electronic Imaging - Digital Photography IX

T2 - Digital Photography IX

Y2 - 4 February 2013 through 6 February 2013

ER -