Shape and texture indexes application to cell nuclei classification

Guillaume Thibault, Bernard Fertil, Claire Navarro, Sandrine Pereira, Pierre Cau, Nicolas Levy, Jean Sequeira, Jean Luc Mari

Research output: Contribution to journalArticle

55 Citations (Scopus)

Abstract

This paper describes the sequence of construction of a cell nuclei classification model by the analysis, the characterization and the classification of shape and texture. We describe first the elaboration of dedicated shape indexes and second the construction of the associated classification submodel. Then we present a new method of texture characterization, based on the construction and the analysis of statistical matrices encoding the texture. The various characterization techniques developed in this paper are systematically compared to previous approaches. In particular, we paid special attention to the results obtained by a versatile classification method using a large range of descriptors dedicated to the characterization of shapes and textures. Finally, the last classifier built with our methods achieved 88% of classification out of the 94% possible.

Original languageEnglish (US)
Article number1357002
JournalInternational Journal of Pattern Recognition and Artificial Intelligence
Volume27
Issue number1
DOIs
StatePublished - Feb 2013
Externally publishedYes

Fingerprint

Textures
Cells
Classifiers

Keywords

  • classification
  • gray level size zone matrix
  • shape and texture characterization
  • Shape and texture indexes

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Computer Vision and Pattern Recognition

Cite this

Shape and texture indexes application to cell nuclei classification. / Thibault, Guillaume; Fertil, Bernard; Navarro, Claire; Pereira, Sandrine; Cau, Pierre; Levy, Nicolas; Sequeira, Jean; Mari, Jean Luc.

In: International Journal of Pattern Recognition and Artificial Intelligence, Vol. 27, No. 1, 1357002, 02.2013.

Research output: Contribution to journalArticle

Thibault, Guillaume ; Fertil, Bernard ; Navarro, Claire ; Pereira, Sandrine ; Cau, Pierre ; Levy, Nicolas ; Sequeira, Jean ; Mari, Jean Luc. / Shape and texture indexes application to cell nuclei classification. In: International Journal of Pattern Recognition and Artificial Intelligence. 2013 ; Vol. 27, No. 1.
@article{dec08a55d64e4e40a0fac9943956cc78,
title = "Shape and texture indexes application to cell nuclei classification",
abstract = "This paper describes the sequence of construction of a cell nuclei classification model by the analysis, the characterization and the classification of shape and texture. We describe first the elaboration of dedicated shape indexes and second the construction of the associated classification submodel. Then we present a new method of texture characterization, based on the construction and the analysis of statistical matrices encoding the texture. The various characterization techniques developed in this paper are systematically compared to previous approaches. In particular, we paid special attention to the results obtained by a versatile classification method using a large range of descriptors dedicated to the characterization of shapes and textures. Finally, the last classifier built with our methods achieved 88{\%} of classification out of the 94{\%} possible.",
keywords = "classification, gray level size zone matrix, shape and texture characterization, Shape and texture indexes",
author = "Guillaume Thibault and Bernard Fertil and Claire Navarro and Sandrine Pereira and Pierre Cau and Nicolas Levy and Jean Sequeira and Mari, {Jean Luc}",
year = "2013",
month = "2",
doi = "10.1142/S0218001413570024",
language = "English (US)",
volume = "27",
journal = "International Journal of Pattern Recognition and Artificial Intelligence",
issn = "0218-0014",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "1",

}

TY - JOUR

T1 - Shape and texture indexes application to cell nuclei classification

AU - Thibault, Guillaume

AU - Fertil, Bernard

AU - Navarro, Claire

AU - Pereira, Sandrine

AU - Cau, Pierre

AU - Levy, Nicolas

AU - Sequeira, Jean

AU - Mari, Jean Luc

PY - 2013/2

Y1 - 2013/2

N2 - This paper describes the sequence of construction of a cell nuclei classification model by the analysis, the characterization and the classification of shape and texture. We describe first the elaboration of dedicated shape indexes and second the construction of the associated classification submodel. Then we present a new method of texture characterization, based on the construction and the analysis of statistical matrices encoding the texture. The various characterization techniques developed in this paper are systematically compared to previous approaches. In particular, we paid special attention to the results obtained by a versatile classification method using a large range of descriptors dedicated to the characterization of shapes and textures. Finally, the last classifier built with our methods achieved 88% of classification out of the 94% possible.

AB - This paper describes the sequence of construction of a cell nuclei classification model by the analysis, the characterization and the classification of shape and texture. We describe first the elaboration of dedicated shape indexes and second the construction of the associated classification submodel. Then we present a new method of texture characterization, based on the construction and the analysis of statistical matrices encoding the texture. The various characterization techniques developed in this paper are systematically compared to previous approaches. In particular, we paid special attention to the results obtained by a versatile classification method using a large range of descriptors dedicated to the characterization of shapes and textures. Finally, the last classifier built with our methods achieved 88% of classification out of the 94% possible.

KW - classification

KW - gray level size zone matrix

KW - shape and texture characterization

KW - Shape and texture indexes

UR - http://www.scopus.com/inward/record.url?scp=84876258818&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876258818&partnerID=8YFLogxK

U2 - 10.1142/S0218001413570024

DO - 10.1142/S0218001413570024

M3 - Article

AN - SCOPUS:84876258818

VL - 27

JO - International Journal of Pattern Recognition and Artificial Intelligence

JF - International Journal of Pattern Recognition and Artificial Intelligence

SN - 0218-0014

IS - 1

M1 - 1357002

ER -