Two-dimensional gray-scale clustering for texture analysis.

Kazunori Yoshiura, K. Tokumori, T. Tanaka, N. Shibaki, S. Ban, K. Araki, S. Kanda

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

OBJECTIVES: To develop a new quantitative method for the visual discrimination of image texture. METHODS: Two kinds of image phantoms were prepared, one for evaluating the effects of change in size and gray values of individual pixels (primitives) on perceived coarseness and the other for evaluating changes in groups of pixels (clusters) on perceived heterogeneity. The phantom images were displayed on a CRT and presented to 11 observers who assessed heterogeneity and coarseness on a 10-point scale between -5 and +5. On the basis of the observers' results, a new texture analysis method termed two-dimensional gray-scale clustering analysis was developed and applied to measure quantitatively the texture of the phantoms. The results obtained were then compared with those of the visual evaluation. RESULTS: The size of the primitives and the clusters greatly affected the visual evaluation of heterogeneity and coarseness. Changes in the gray value had only a slight effect. The intra-observer variation for heterogeneity was significantly larger than that for coarseness. Two-dimensional gray-scale clustering analysis could differentiate heterogeneity from coarseness. A high correlation was obtained between the visual evaluation and the quantitative data. CONCLUSION: Quantitative two-dimensional gray-scale clustering analysis appears to be a useful means of texture analysis.

Original languageEnglish
Pages (from-to)152-160
Number of pages9
JournalDento maxillo facial radiology
Volume26
Issue number3
DOIs
Publication statusPublished - Jan 1 1997

Fingerprint

Cluster Analysis
Observer Variation

All Science Journal Classification (ASJC) codes

  • Otorhinolaryngology
  • Radiology Nuclear Medicine and imaging
  • Dentistry(all)

Cite this

Yoshiura, K., Tokumori, K., Tanaka, T., Shibaki, N., Ban, S., Araki, K., & Kanda, S. (1997). Two-dimensional gray-scale clustering for texture analysis. Dento maxillo facial radiology, 26(3), 152-160. https://doi.org/10.1038/sj.dmfr.4600229

Two-dimensional gray-scale clustering for texture analysis. / Yoshiura, Kazunori; Tokumori, K.; Tanaka, T.; Shibaki, N.; Ban, S.; Araki, K.; Kanda, S.

In: Dento maxillo facial radiology, Vol. 26, No. 3, 01.01.1997, p. 152-160.

Research output: Contribution to journalArticle

Yoshiura, K, Tokumori, K, Tanaka, T, Shibaki, N, Ban, S, Araki, K & Kanda, S 1997, 'Two-dimensional gray-scale clustering for texture analysis.', Dento maxillo facial radiology, vol. 26, no. 3, pp. 152-160. https://doi.org/10.1038/sj.dmfr.4600229
Yoshiura, Kazunori ; Tokumori, K. ; Tanaka, T. ; Shibaki, N. ; Ban, S. ; Araki, K. ; Kanda, S. / Two-dimensional gray-scale clustering for texture analysis. In: Dento maxillo facial radiology. 1997 ; Vol. 26, No. 3. pp. 152-160.
@article{68bc2cd86c4c40ea891660001f21ad84,
title = "Two-dimensional gray-scale clustering for texture analysis.",
abstract = "OBJECTIVES: To develop a new quantitative method for the visual discrimination of image texture. METHODS: Two kinds of image phantoms were prepared, one for evaluating the effects of change in size and gray values of individual pixels (primitives) on perceived coarseness and the other for evaluating changes in groups of pixels (clusters) on perceived heterogeneity. The phantom images were displayed on a CRT and presented to 11 observers who assessed heterogeneity and coarseness on a 10-point scale between -5 and +5. On the basis of the observers' results, a new texture analysis method termed two-dimensional gray-scale clustering analysis was developed and applied to measure quantitatively the texture of the phantoms. The results obtained were then compared with those of the visual evaluation. RESULTS: The size of the primitives and the clusters greatly affected the visual evaluation of heterogeneity and coarseness. Changes in the gray value had only a slight effect. The intra-observer variation for heterogeneity was significantly larger than that for coarseness. Two-dimensional gray-scale clustering analysis could differentiate heterogeneity from coarseness. A high correlation was obtained between the visual evaluation and the quantitative data. CONCLUSION: Quantitative two-dimensional gray-scale clustering analysis appears to be a useful means of texture analysis.",
author = "Kazunori Yoshiura and K. Tokumori and T. Tanaka and N. Shibaki and S. Ban and K. Araki and S. Kanda",
year = "1997",
month = "1",
day = "1",
doi = "10.1038/sj.dmfr.4600229",
language = "English",
volume = "26",
pages = "152--160",
journal = "Dentomaxillofacial Radiology",
issn = "0250-832X",
publisher = "British Institute of Radiology",
number = "3",

}

TY - JOUR

T1 - Two-dimensional gray-scale clustering for texture analysis.

AU - Yoshiura, Kazunori

AU - Tokumori, K.

AU - Tanaka, T.

AU - Shibaki, N.

AU - Ban, S.

AU - Araki, K.

AU - Kanda, S.

PY - 1997/1/1

Y1 - 1997/1/1

N2 - OBJECTIVES: To develop a new quantitative method for the visual discrimination of image texture. METHODS: Two kinds of image phantoms were prepared, one for evaluating the effects of change in size and gray values of individual pixels (primitives) on perceived coarseness and the other for evaluating changes in groups of pixels (clusters) on perceived heterogeneity. The phantom images were displayed on a CRT and presented to 11 observers who assessed heterogeneity and coarseness on a 10-point scale between -5 and +5. On the basis of the observers' results, a new texture analysis method termed two-dimensional gray-scale clustering analysis was developed and applied to measure quantitatively the texture of the phantoms. The results obtained were then compared with those of the visual evaluation. RESULTS: The size of the primitives and the clusters greatly affected the visual evaluation of heterogeneity and coarseness. Changes in the gray value had only a slight effect. The intra-observer variation for heterogeneity was significantly larger than that for coarseness. Two-dimensional gray-scale clustering analysis could differentiate heterogeneity from coarseness. A high correlation was obtained between the visual evaluation and the quantitative data. CONCLUSION: Quantitative two-dimensional gray-scale clustering analysis appears to be a useful means of texture analysis.

AB - OBJECTIVES: To develop a new quantitative method for the visual discrimination of image texture. METHODS: Two kinds of image phantoms were prepared, one for evaluating the effects of change in size and gray values of individual pixels (primitives) on perceived coarseness and the other for evaluating changes in groups of pixels (clusters) on perceived heterogeneity. The phantom images were displayed on a CRT and presented to 11 observers who assessed heterogeneity and coarseness on a 10-point scale between -5 and +5. On the basis of the observers' results, a new texture analysis method termed two-dimensional gray-scale clustering analysis was developed and applied to measure quantitatively the texture of the phantoms. The results obtained were then compared with those of the visual evaluation. RESULTS: The size of the primitives and the clusters greatly affected the visual evaluation of heterogeneity and coarseness. Changes in the gray value had only a slight effect. The intra-observer variation for heterogeneity was significantly larger than that for coarseness. Two-dimensional gray-scale clustering analysis could differentiate heterogeneity from coarseness. A high correlation was obtained between the visual evaluation and the quantitative data. CONCLUSION: Quantitative two-dimensional gray-scale clustering analysis appears to be a useful means of texture analysis.

UR - http://www.scopus.com/inward/record.url?scp=0031129596&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031129596&partnerID=8YFLogxK

U2 - 10.1038/sj.dmfr.4600229

DO - 10.1038/sj.dmfr.4600229

M3 - Article

VL - 26

SP - 152

EP - 160

JO - Dentomaxillofacial Radiology

JF - Dentomaxillofacial Radiology

SN - 0250-832X

IS - 3

ER -