Skip to Main content Skip to Navigation
Conference papers

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.
Complete list of metadata

Cited literature [13 references]  Display  Hide  Download

https://hal-mines-paristech.archives-ouvertes.fr/hal-00834446
Contributor : Bibliothèque Mines Paristech <>
Submitted on : Saturday, June 15, 2013 - 10:12:23 AM
Last modification on : Thursday, September 24, 2020 - 4:38:03 PM
Long-term archiving on: : Monday, September 16, 2013 - 4:03:56 AM

File

EfficientStatisticalMorphologi...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00834446, version 1

Citation

Guillaume Thibault, Jesus Angulo. Efficient statistical/morphological cell texture characterization and classification. 21th International Conference on Pattern Recognition (ICPR), Nov 2012, Tsukuba, Japan. pp.2440-2443. ⟨hal-00834446⟩

Share

Metrics

Record views

270

Files downloads

401