Efficient statistical/morphological cell texture characterization and classification

Guillaume Thibault, Jesus Angulo

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

16 Citations (Scopus)

Abstract

This paper presents the different steps for an automatic fluorescence-labelled cell classification method. First a data features study is discussed in order to describe cell texture by means of morphological and statistical texture descriptors. Then, results on supervised classification using logistic regression, random forest and neural networks, for both morphological and statistical descriptors, is presented. We propose a final consolidated classifier based on a weighted probability for each class, where the weights are given by the empirical classification performances. The method is evaluated on ICPR'12 HEp-2 dataset contest.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages2440-2443
Number of pages4
StatePublished - 2012
Externally publishedYes
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
Duration: Nov 11 2012Nov 15 2012

Other

Other21st International Conference on Pattern Recognition, ICPR 2012
CountryJapan
CityTsukuba
Period11/11/1211/15/12

Fingerprint

Textures
Logistics
Classifiers
Fluorescence
Neural networks

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Thibault, G., & Angulo, J. (2012). Efficient statistical/morphological cell texture characterization and classification. In Proceedings - International Conference on Pattern Recognition (pp. 2440-2443). [6460660]

Efficient statistical/morphological cell texture characterization and classification. / Thibault, Guillaume; Angulo, Jesus.

Proceedings - International Conference on Pattern Recognition. 2012. p. 2440-2443 6460660.

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

Thibault, G & Angulo, J 2012, Efficient statistical/morphological cell texture characterization and classification. in Proceedings - International Conference on Pattern Recognition., 6460660, pp. 2440-2443, 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, 11/11/12.
Thibault G, Angulo J. Efficient statistical/morphological cell texture characterization and classification. In Proceedings - International Conference on Pattern Recognition. 2012. p. 2440-2443. 6460660
Thibault, Guillaume ; Angulo, Jesus. / Efficient statistical/morphological cell texture characterization and classification. Proceedings - International Conference on Pattern Recognition. 2012. pp. 2440-2443
@inproceedings{63e0e197163a402190e057f4027872ed,
title = "Efficient statistical/morphological cell texture characterization and classification",
abstract = "This paper presents the different steps for an automatic fluorescence-labelled cell classification method. First a data features study is discussed in order to describe cell texture by means of morphological and statistical texture descriptors. Then, results on supervised classification using logistic regression, random forest and neural networks, for both morphological and statistical descriptors, is presented. We propose a final consolidated classifier based on a weighted probability for each class, where the weights are given by the empirical classification performances. The method is evaluated on ICPR'12 HEp-2 dataset contest.",
author = "Guillaume Thibault and Jesus Angulo",
year = "2012",
language = "English (US)",
isbn = "9784990644109",
pages = "2440--2443",
booktitle = "Proceedings - International Conference on Pattern Recognition",

}

TY - GEN

T1 - Efficient statistical/morphological cell texture characterization and classification

AU - Thibault, Guillaume

AU - Angulo, Jesus

PY - 2012

Y1 - 2012

N2 - This paper presents the different steps for an automatic fluorescence-labelled cell classification method. First a data features study is discussed in order to describe cell texture by means of morphological and statistical texture descriptors. Then, results on supervised classification using logistic regression, random forest and neural networks, for both morphological and statistical descriptors, is presented. We propose a final consolidated classifier based on a weighted probability for each class, where the weights are given by the empirical classification performances. The method is evaluated on ICPR'12 HEp-2 dataset contest.

AB - This paper presents the different steps for an automatic fluorescence-labelled cell classification method. First a data features study is discussed in order to describe cell texture by means of morphological and statistical texture descriptors. Then, results on supervised classification using logistic regression, random forest and neural networks, for both morphological and statistical descriptors, is presented. We propose a final consolidated classifier based on a weighted probability for each class, where the weights are given by the empirical classification performances. The method is evaluated on ICPR'12 HEp-2 dataset contest.

UR - http://www.scopus.com/inward/record.url?scp=84874574883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874574883&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84874574883

SN - 9784990644109

SP - 2440

EP - 2443

BT - Proceedings - International Conference on Pattern Recognition

ER -