Advanced statistical matrices for texture characterization

Application to cell classification

Guillaume Thibault, Jesús Angulo, Fernand Meyer

Research output: Contribution to journalArticle

51 Citations (Scopus)

Abstract

This paper presents new structural statistical matrices which are gray level size zone matrix (SZM) texture descriptor variants. The SZM is based on the cooccurrences of size/intensity of each flat zone (connected pixels with the same gray level). The first improvement increases the information processed by merging multiple gray-level quantizations and reduces the required parameter numbers. New improved descriptors were especially designed for supervised cell texture classification. They are illustrated thanks to two different databases built from quantitative cell biology. The second alternative characterizes the DNA organization during the mitosis, according to zone intensities radial distribution. The third variant is a matrix structure generalization for the fibrous texture analysis, by changing the intensity/size pair into the length/orientation pair of each region.

Original languageEnglish (US)
Article number6621011
Pages (from-to)630-637
Number of pages8
JournalIEEE Transactions on Biomedical Engineering
Volume61
Issue number3
DOIs
StatePublished - Mar 2014
Externally publishedYes

Fingerprint

Textures
Cytology
Merging
DNA
Pixels

Keywords

  • Gray-level size zone matrix (SZM)
  • quantitative cytology
  • structural statistical matrices
  • texture characterization and classification

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Advanced statistical matrices for texture characterization : Application to cell classification. / Thibault, Guillaume; Angulo, Jesús; Meyer, Fernand.

In: IEEE Transactions on Biomedical Engineering, Vol. 61, No. 3, 6621011, 03.2014, p. 630-637.

Research output: Contribution to journalArticle

@article{b0a6f2a6f477447f93fa0e7cab5ecbb5,
title = "Advanced statistical matrices for texture characterization: Application to cell classification",
abstract = "This paper presents new structural statistical matrices which are gray level size zone matrix (SZM) texture descriptor variants. The SZM is based on the cooccurrences of size/intensity of each flat zone (connected pixels with the same gray level). The first improvement increases the information processed by merging multiple gray-level quantizations and reduces the required parameter numbers. New improved descriptors were especially designed for supervised cell texture classification. They are illustrated thanks to two different databases built from quantitative cell biology. The second alternative characterizes the DNA organization during the mitosis, according to zone intensities radial distribution. The third variant is a matrix structure generalization for the fibrous texture analysis, by changing the intensity/size pair into the length/orientation pair of each region.",
keywords = "Gray-level size zone matrix (SZM), quantitative cytology, structural statistical matrices, texture characterization and classification",
author = "Guillaume Thibault and Jes{\'u}s Angulo and Fernand Meyer",
year = "2014",
month = "3",
doi = "10.1109/TBME.2013.2284600",
language = "English (US)",
volume = "61",
pages = "630--637",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "3",

}

TY - JOUR

T1 - Advanced statistical matrices for texture characterization

T2 - Application to cell classification

AU - Thibault, Guillaume

AU - Angulo, Jesús

AU - Meyer, Fernand

PY - 2014/3

Y1 - 2014/3

N2 - This paper presents new structural statistical matrices which are gray level size zone matrix (SZM) texture descriptor variants. The SZM is based on the cooccurrences of size/intensity of each flat zone (connected pixels with the same gray level). The first improvement increases the information processed by merging multiple gray-level quantizations and reduces the required parameter numbers. New improved descriptors were especially designed for supervised cell texture classification. They are illustrated thanks to two different databases built from quantitative cell biology. The second alternative characterizes the DNA organization during the mitosis, according to zone intensities radial distribution. The third variant is a matrix structure generalization for the fibrous texture analysis, by changing the intensity/size pair into the length/orientation pair of each region.

AB - This paper presents new structural statistical matrices which are gray level size zone matrix (SZM) texture descriptor variants. The SZM is based on the cooccurrences of size/intensity of each flat zone (connected pixels with the same gray level). The first improvement increases the information processed by merging multiple gray-level quantizations and reduces the required parameter numbers. New improved descriptors were especially designed for supervised cell texture classification. They are illustrated thanks to two different databases built from quantitative cell biology. The second alternative characterizes the DNA organization during the mitosis, according to zone intensities radial distribution. The third variant is a matrix structure generalization for the fibrous texture analysis, by changing the intensity/size pair into the length/orientation pair of each region.

KW - Gray-level size zone matrix (SZM)

KW - quantitative cytology

KW - structural statistical matrices

KW - texture characterization and classification

UR - http://www.scopus.com/inward/record.url?scp=84896867733&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896867733&partnerID=8YFLogxK

U2 - 10.1109/TBME.2013.2284600

DO - 10.1109/TBME.2013.2284600

M3 - Article

VL - 61

SP - 630

EP - 637

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 3

M1 - 6621011

ER -