HEp-2 Cell Classification with heterogeneous classes-processes based on K-Nearest Neighbours

Marco Cipolla, Vincenzo Taormina, Donato Cascio, Francesco Fauci, Giuseppe Raso, Simone Maria Vasile, Vincenzo Taormina

Risultato della ricerca: Other

15 Citazioni (Scopus)

Abstract

We present a scheme for the feature extraction and classification of the fluorescence staining patterns of HEp-2 cells in IIF images. We propose a set ofcomplementary processes specific to each class of patterns to search. Our set of processes consists of preprocessing,features extraction and classification. The choice of methods, features and parameters was performedautomatically, using the Mean Class Accuracy (MCA) as a figure of merit. We extract a large number (108) of features able to fully characterize the staining pattern of HEp-2 cells. We propose a classification approach basedon two steps: the first step follows the one-against-all(OAA) scheme, while the second step follows the one-against-one (OAO) scheme. To do this, we needed to implement 21 KNN classifiers: 6 OAA and 15 OAO.Leave-one-out image cross validation method was used for the evaluation of the results.
Lingua originaleEnglish
Pagine10-15
Numero di pagine6
Stato di pubblicazionePublished - 2014

Fingerprint

Feature extraction
Classifiers
Fluorescence

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cita questo

@conference{9e5c965a996348e5aac96bcf0a9df983,
title = "HEp-2 Cell Classification with heterogeneous classes-processes based on K-Nearest Neighbours",
abstract = "We present a scheme for the feature extraction and classification of the fluorescence staining patterns of HEp-2 cells in IIF images. We propose a set ofcomplementary processes specific to each class of patterns to search. Our set of processes consists of preprocessing,features extraction and classification. The choice of methods, features and parameters was performedautomatically, using the Mean Class Accuracy (MCA) as a figure of merit. We extract a large number (108) of features able to fully characterize the staining pattern of HEp-2 cells. We propose a classification approach basedon two steps: the first step follows the one-against-all(OAA) scheme, while the second step follows the one-against-one (OAO) scheme. To do this, we needed to implement 21 KNN classifiers: 6 OAA and 15 OAO.Leave-one-out image cross validation method was used for the evaluation of the results.",
author = "Marco Cipolla and Vincenzo Taormina and Donato Cascio and Francesco Fauci and Giuseppe Raso and Vasile, {Simone Maria} and Vincenzo Taormina",
year = "2014",
language = "English",
pages = "10--15",

}

TY - CONF

T1 - HEp-2 Cell Classification with heterogeneous classes-processes based on K-Nearest Neighbours

AU - Cipolla, Marco

AU - Taormina, Vincenzo

AU - Cascio, Donato

AU - Fauci, Francesco

AU - Raso, Giuseppe

AU - Vasile, Simone Maria

AU - Taormina, Vincenzo

PY - 2014

Y1 - 2014

N2 - We present a scheme for the feature extraction and classification of the fluorescence staining patterns of HEp-2 cells in IIF images. We propose a set ofcomplementary processes specific to each class of patterns to search. Our set of processes consists of preprocessing,features extraction and classification. The choice of methods, features and parameters was performedautomatically, using the Mean Class Accuracy (MCA) as a figure of merit. We extract a large number (108) of features able to fully characterize the staining pattern of HEp-2 cells. We propose a classification approach basedon two steps: the first step follows the one-against-all(OAA) scheme, while the second step follows the one-against-one (OAO) scheme. To do this, we needed to implement 21 KNN classifiers: 6 OAA and 15 OAO.Leave-one-out image cross validation method was used for the evaluation of the results.

AB - We present a scheme for the feature extraction and classification of the fluorescence staining patterns of HEp-2 cells in IIF images. We propose a set ofcomplementary processes specific to each class of patterns to search. Our set of processes consists of preprocessing,features extraction and classification. The choice of methods, features and parameters was performedautomatically, using the Mean Class Accuracy (MCA) as a figure of merit. We extract a large number (108) of features able to fully characterize the staining pattern of HEp-2 cells. We propose a classification approach basedon two steps: the first step follows the one-against-all(OAA) scheme, while the second step follows the one-against-one (OAO) scheme. To do this, we needed to implement 21 KNN classifiers: 6 OAA and 15 OAO.Leave-one-out image cross validation method was used for the evaluation of the results.

UR - http://hdl.handle.net/10447/105511

UR - http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6973539

M3 - Other

SP - 10

EP - 15

ER -