Advanced statistical matrices for texture characterization

Application to DNA chromatin and microtubule network classification

Guillaume Thibault, Jesús Angulo, Fernand Meyer

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

6 Citations (Scopus)

Abstract

This paper presents significant improvements of Gray Level Size Zone Matrix (GLSZM) which is a bivariate statistical representation of texture, based on the co-occurrences of size/intensity of each flat zone (connected pixels of the same gray level). The first improvement is a multi-scale extension of the matrix which merges various quantizations of gray levels. A second alternative is proposed to take into account radial distribution of zone intensities. The third variant is a generalization of the matrix structure which allows to analyze fibrous textures, by changing the pair intensity/size for the pair length/orientation of each region. The interest of these improved descriptors is illustrated by texture classification problems arising from quantitative cell biology.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages53-56
Number of pages4
DOIs
StatePublished - 2011
Externally publishedYes
Event2011 18th IEEE International Conference on Image Processing, ICIP 2011 - Brussels, Belgium
Duration: Sep 11 2011Sep 14 2011

Other

Other2011 18th IEEE International Conference on Image Processing, ICIP 2011
CountryBelgium
CityBrussels
Period9/11/119/14/11

Fingerprint

DNA
Textures
Cytology
Pixels

Keywords

  • Gray Level Size Zone Matrix (GLSZM)
  • Structural Statistical Matrices
  • Texture Characterization

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Thibault, G., Angulo, J., & Meyer, F. (2011). Advanced statistical matrices for texture characterization: Application to DNA chromatin and microtubule network classification. In Proceedings - International Conference on Image Processing, ICIP (pp. 53-56). [6116401] https://doi.org/10.1109/ICIP.2011.6116401

Advanced statistical matrices for texture characterization : Application to DNA chromatin and microtubule network classification. / Thibault, Guillaume; Angulo, Jesús; Meyer, Fernand.

Proceedings - International Conference on Image Processing, ICIP. 2011. p. 53-56 6116401.

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

Thibault, G, Angulo, J & Meyer, F 2011, Advanced statistical matrices for texture characterization: Application to DNA chromatin and microtubule network classification. in Proceedings - International Conference on Image Processing, ICIP., 6116401, pp. 53-56, 2011 18th IEEE International Conference on Image Processing, ICIP 2011, Brussels, Belgium, 9/11/11. https://doi.org/10.1109/ICIP.2011.6116401
Thibault, Guillaume ; Angulo, Jesús ; Meyer, Fernand. / Advanced statistical matrices for texture characterization : Application to DNA chromatin and microtubule network classification. Proceedings - International Conference on Image Processing, ICIP. 2011. pp. 53-56
@inproceedings{78e7136726d34c65882952a40623db81,
title = "Advanced statistical matrices for texture characterization: Application to DNA chromatin and microtubule network classification",
abstract = "This paper presents significant improvements of Gray Level Size Zone Matrix (GLSZM) which is a bivariate statistical representation of texture, based on the co-occurrences of size/intensity of each flat zone (connected pixels of the same gray level). The first improvement is a multi-scale extension of the matrix which merges various quantizations of gray levels. A second alternative is proposed to take into account radial distribution of zone intensities. The third variant is a generalization of the matrix structure which allows to analyze fibrous textures, by changing the pair intensity/size for the pair length/orientation of each region. The interest of these improved descriptors is illustrated by texture classification problems arising from quantitative cell biology.",
keywords = "Gray Level Size Zone Matrix (GLSZM), Structural Statistical Matrices, Texture Characterization",
author = "Guillaume Thibault and Jes{\'u}s Angulo and Fernand Meyer",
year = "2011",
doi = "10.1109/ICIP.2011.6116401",
language = "English (US)",
isbn = "9781457713033",
pages = "53--56",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Advanced statistical matrices for texture characterization

T2 - Application to DNA chromatin and microtubule network classification

AU - Thibault, Guillaume

AU - Angulo, Jesús

AU - Meyer, Fernand

PY - 2011

Y1 - 2011

N2 - This paper presents significant improvements of Gray Level Size Zone Matrix (GLSZM) which is a bivariate statistical representation of texture, based on the co-occurrences of size/intensity of each flat zone (connected pixels of the same gray level). The first improvement is a multi-scale extension of the matrix which merges various quantizations of gray levels. A second alternative is proposed to take into account radial distribution of zone intensities. The third variant is a generalization of the matrix structure which allows to analyze fibrous textures, by changing the pair intensity/size for the pair length/orientation of each region. The interest of these improved descriptors is illustrated by texture classification problems arising from quantitative cell biology.

AB - This paper presents significant improvements of Gray Level Size Zone Matrix (GLSZM) which is a bivariate statistical representation of texture, based on the co-occurrences of size/intensity of each flat zone (connected pixels of the same gray level). The first improvement is a multi-scale extension of the matrix which merges various quantizations of gray levels. A second alternative is proposed to take into account radial distribution of zone intensities. The third variant is a generalization of the matrix structure which allows to analyze fibrous textures, by changing the pair intensity/size for the pair length/orientation of each region. The interest of these improved descriptors is illustrated by texture classification problems arising from quantitative cell biology.

KW - Gray Level Size Zone Matrix (GLSZM)

KW - Structural Statistical Matrices

KW - Texture Characterization

UR - http://www.scopus.com/inward/record.url?scp=84856243899&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856243899&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2011.6116401

DO - 10.1109/ICIP.2011.6116401

M3 - Conference contribution

SN - 9781457713033

SP - 53

EP - 56

BT - Proceedings - International Conference on Image Processing, ICIP

ER -