Structural texture similarity metrics for retrieval applications

Xiaonan Zhao; Matthew G. Reyes; Thrasyvoulos N Pappas; David L. Neuhoff

doi:10.1109/ICIP.2008.4711975

Structural texture similarity metrics for retrieval applications

Xiaonan Zhao^*, Matthew G. Reyes, Thrasyvoulos N Pappas, David L. Neuhoff

^*Corresponding author for this work

Electrical and Computer Engineering

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

53 Scopus citations

Abstract

Traditional image similarity metrics compare two images on a point-by-point basis. On the other hand, structural similarity metrics (SSIM) attempt to base image similarity on "structural" information. We evaluate the performance of SSIM metrics in the context of texture similarity, and propose new metrics that incorporate the best features of SSIM and eliminate the most serious drawbacks. We show that the proposed new texture similarity metrics outperform SSIM and its variations, as well as PSNR and other traditional metrics. We demonstrate the advantages of the new metrics on a carefully selected set of 39 texture pairs and comparisons with informal subjective test results.

Original language	English (US)
Title of host publication	2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings
Pages	1196-1199
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2008.4711975
State	Published - Dec 1 2008
Event	2008 IEEE International Conference on Image Processing, ICIP 2008 - San Diego, CA, United States Duration: Oct 12 2008 → Oct 15 2008

Other

Other	2008 IEEE International Conference on Image Processing, ICIP 2008
Country/Territory	United States
City	San Diego, CA
Period	10/12/08 → 10/15/08

Keywords

Content-based retrieval
Texture similarity

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2008.4711975

Cite this

@inproceedings{51b7f8b9617e4b42b7f3adcfaf6e2832,

title = "Structural texture similarity metrics for retrieval applications",

abstract = "Traditional image similarity metrics compare two images on a point-by-point basis. On the other hand, structural similarity metrics (SSIM) attempt to base image similarity on {"}structural{"} information. We evaluate the performance of SSIM metrics in the context of texture similarity, and propose new metrics that incorporate the best features of SSIM and eliminate the most serious drawbacks. We show that the proposed new texture similarity metrics outperform SSIM and its variations, as well as PSNR and other traditional metrics. We demonstrate the advantages of the new metrics on a carefully selected set of 39 texture pairs and comparisons with informal subjective test results.",

keywords = "Content-based retrieval, Texture similarity",

author = "Xiaonan Zhao and Reyes, {Matthew G.} and Pappas, {Thrasyvoulos N} and Neuhoff, {David L.}",

year = "2008",

month = dec,

day = "1",

doi = "10.1109/ICIP.2008.4711975",

language = "English (US)",

isbn = "1424417643",

pages = "1196--1199",

booktitle = "2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings",

note = "2008 IEEE International Conference on Image Processing, ICIP 2008 ; Conference date: 12-10-2008 Through 15-10-2008",

}

Zhao, X, Reyes, MG, Pappas, TN & Neuhoff, DL 2008, Structural texture similarity metrics for retrieval applications. in 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings., 4711975, pp. 1196-1199, 2008 IEEE International Conference on Image Processing, ICIP 2008, San Diego, CA, United States, 10/12/08. https://doi.org/10.1109/ICIP.2008.4711975

TY - GEN

T1 - Structural texture similarity metrics for retrieval applications

AU - Zhao, Xiaonan

AU - Reyes, Matthew G.

AU - Pappas, Thrasyvoulos N

AU - Neuhoff, David L.

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Traditional image similarity metrics compare two images on a point-by-point basis. On the other hand, structural similarity metrics (SSIM) attempt to base image similarity on "structural" information. We evaluate the performance of SSIM metrics in the context of texture similarity, and propose new metrics that incorporate the best features of SSIM and eliminate the most serious drawbacks. We show that the proposed new texture similarity metrics outperform SSIM and its variations, as well as PSNR and other traditional metrics. We demonstrate the advantages of the new metrics on a carefully selected set of 39 texture pairs and comparisons with informal subjective test results.

AB - Traditional image similarity metrics compare two images on a point-by-point basis. On the other hand, structural similarity metrics (SSIM) attempt to base image similarity on "structural" information. We evaluate the performance of SSIM metrics in the context of texture similarity, and propose new metrics that incorporate the best features of SSIM and eliminate the most serious drawbacks. We show that the proposed new texture similarity metrics outperform SSIM and its variations, as well as PSNR and other traditional metrics. We demonstrate the advantages of the new metrics on a carefully selected set of 39 texture pairs and comparisons with informal subjective test results.

KW - Content-based retrieval

KW - Texture similarity

UR - http://www.scopus.com/inward/record.url?scp=69949140365&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69949140365&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2008.4711975

DO - 10.1109/ICIP.2008.4711975

M3 - Conference contribution

AN - SCOPUS:69949140365

SN - 1424417643

SN - 9781424417643

SP - 1196

EP - 1199

BT - 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings

T2 - 2008 IEEE International Conference on Image Processing, ICIP 2008

Y2 - 12 October 2008 through 15 October 2008

ER -

Structural texture similarity metrics for retrieval applications

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this