RSurf - the Efficient Texture-Based Descriptor for Fluorescence
Microscopy Images of HEp-2 Cells

D 2014

RSurf - the Efficient Texture-Based Descriptor for Fluorescence Microscopy Images of HEp-2 Cells

MAJTNER, Tomáš, Roman STOKLASA and David SVOBODA

Basic information

Original name

RSurf - the Efficient Texture-Based Descriptor for Fluorescence Microscopy Images of HEp-2 Cells

Authors

MAJTNER, Tomáš (703 Slovakia, guarantor, belonging to the institution), Roman STOKLASA (703 Slovakia, belonging to the institution) and David SVOBODA (203 Czech Republic, belonging to the institution)

Edition

Los Alamitos, California, 22nd International Conference on Pattern Recognition, p. 1194-1199, 6 pp. 2014

Publisher

IEEE Computer Society

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

20200 2.2 Electrical engineering, Electronic engineering, Information engineering

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

storage medium (CD, DVD, flash disk)

RIV identification code

RIV/00216224:14330/14:00073550

Organization unit

Faculty of Informatics

ISBN

978-1-4799-5208-3

ISSN

DOI

http://dx.doi.org/10.1109/ICPR.2014.215

UT WoS

000359818001053

Keywords in English

texture descriptor;rsurf;hep-2

Abstract

V originále

In biomedical image analysis, object description and classification tasks are very common. Our work relates to the problem of classification of Human Epithelial (HEp-2) cells. Since the crucial part of each classification process is the feature extraction and selection, much attention should be concentrated to the development of proper image descriptors. In this article, we introduce a new efficient texture-based image descriptor for HEp-2 images. We compare proposed descriptor with LBP, Haralick features (GLCM statistics) and Tamura features using the public MIVIA HEp-2 Images Dataset. Our descriptor outperforms all previously mentioned approaches and the classifier based solely on the proposed descriptor is able to achieve the accuracy as high as 87.8%.

Links

GBP302/12/G157, research and development project

Name: Dynamika a organizace chromosomů během buněčného cyklu a při diferenciaci v normě a patologii

Investor: Czech Science Foundation

MUNI/A/0765/2013, interní kód MU

Name: Zapojení studentů Fakulty informatiky do mezinárodní vědecké komunity (Acronym: SKOMU)

Investor: Masaryk University, Category A

MUNI/A/0855/2013, interní kód MU

Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace III. (Acronym: FI MAV III.)

Investor: Masaryk University, Category A

Citovat

MAJTNER, Tomáš, Roman STOKLASA and David SVOBODA. RSurf - the Efficient Texture-Based Descriptor for Fluorescence Microscopy Images of HEp-2 Cells. In 22nd International Conference on Pattern Recognition. Los Alamitos, California: IEEE Computer Society, 2014, p. 1194-1199. ISBN 978-1-4799-5208-3. Available from: https://dx.doi.org/10.1109/ICPR.2014.215.

@inproceedings{1173479,
   author = {Majtner, Tomáš and Stoklasa, Roman and Svoboda, David},
   address = {Los Alamitos, California},
   booktitle = {22nd International Conference on Pattern Recognition},
   doi = {http://dx.doi.org/10.1109/ICPR.2014.215},
   keywords = {texture descriptor;rsurf;hep-2},
   howpublished = {paměťový nosič},
   language = {eng},
   location = {Los Alamitos, California},
   isbn = {978-1-4799-5208-3},
   pages = {1194-1199},
   publisher = {IEEE Computer Society},
   title = {RSurf - the Efficient Texture-Based Descriptor for Fluorescence Microscopy Images of HEp-2 Cells},
   year = {2014}
}

TY  - JOUR
ID  - 1173479
AU  - Majtner, Tomáš - Stoklasa, Roman - Svoboda, David
PY  - 2014
TI  - RSurf - the Efficient Texture-Based Descriptor for Fluorescence Microscopy Images of HEp-2 Cells
PB  - IEEE Computer Society
CY  - Los Alamitos, California
SN  - 9781479952083
KW  - texture descriptor;rsurf;hep-2
N2  - In biomedical image analysis, object description and classification tasks are very common. Our work relates to the problem of classification of Human Epithelial (HEp-2) cells. Since the crucial part of each classification process is the feature extraction and selection, much attention should be concentrated to the development of proper image descriptors. In this article, we introduce a new efficient texture-based image descriptor for HEp-2 images. We compare proposed descriptor with LBP, Haralick features (GLCM statistics) and Tamura features using the public MIVIA HEp-2 Images Dataset. Our descriptor outperforms all previously mentioned approaches and the classifier based solely on the proposed descriptor is able to achieve the accuracy as high as 87.8%.
ER  -

MAJTNER, Tomáš, Roman STOKLASA and David SVOBODA. RSurf - the Efficient Texture-Based Descriptor for Fluorescence Microscopy Images of HEp-2 Cells. In \textit{22nd International Conference on Pattern Recognition}. Los Alamitos, California: IEEE Computer Society, 2014, p.~1194-1199. ISBN~978-1-4799-5208-3. Available from: https://dx.doi.org/10.1109/ICPR.2014.215.

Detailed Information on Publication Record