Texture Analysis Using 3D Gabor Features and 3D MPEG-7 Edge
Histogram Descriptor in Fluorescence Microscopy

D 2014

Texture Analysis Using 3D Gabor Features and 3D MPEG-7 Edge Histogram Descriptor in Fluorescence Microscopy

MAJTNER, Tomáš and David SVOBODA

Basic information

Original name

Texture Analysis Using 3D Gabor Features and 3D MPEG-7 Edge Histogram Descriptor in Fluorescence Microscopy

Authors

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

Edition

Los Alamitos, California, 4th International Conference on 3D Imaging (IC3D), p. 1-7, 7 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

electronic version available online

RIV identification code

RIV/00216224:14330/14:00074031

Organization unit

Faculty of Informatics

ISBN

978-1-4799-8023-9

DOI

http://dx.doi.org/10.1109/IC3D.2014.7032576

UT WoS

000380557000005

Keywords in English

3D images; Edge Histogram Descriptor; Gabor filters; fluorescence microscopy

Abstract

V originále

The pattern recognition with focus on texture and shape analysis is still very hot topic, especially in biomedical image processing. In this article, we introduce 3D extension of well-known approaches for this particular area. We focus on the collection of MPEG-7 image descriptors, specifically on Edge Histogram Descriptor (EHD) and Gabor features, which are core of Homogeneous Texture Descriptor (HTD). The proposed extensions are evaluated on the dataset consisting of three classes of 3D volumetric biomedical images. Two different classifiers, namely $k$-NN and Multi-Class SVM, are used to evaluate the proposed algorithms. According to the presented tests, proposed 3D extensions clearly outperforms their 2D equivalents in the classification tasks.

Links

GA14-22461S, research and development project

Name: Vývoj a studium metod pro kvantifikaci živých buněk (Acronym: Live Cell Quantification)

Investor: Czech Science Foundation

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 and David SVOBODA. Texture Analysis Using 3D Gabor Features and 3D MPEG-7 Edge Histogram Descriptor in Fluorescence Microscopy. Online. In 4th International Conference on 3D Imaging (IC3D). Los Alamitos, California: IEEE Computer Society, 2014, p. 1-7. ISBN 978-1-4799-8023-9. Available from: https://dx.doi.org/10.1109/IC3D.2014.7032576.

@inproceedings{1204559,
   author = {Majtner, Tomáš and Svoboda, David},
   address = {Los Alamitos, California},
   booktitle = {4th International Conference on 3D Imaging (IC3D)},
   doi = {http://dx.doi.org/10.1109/IC3D.2014.7032576},
   keywords = {3D images; Edge Histogram Descriptor; Gabor filters; fluorescence microscopy},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Los Alamitos, California},
   isbn = {978-1-4799-8023-9},
   pages = {1-7},
   publisher = {IEEE Computer Society},
   title = {Texture Analysis Using 3D Gabor Features and 3D MPEG-7 Edge Histogram Descriptor in Fluorescence Microscopy},
   year = {2014}
}

TY  - JOUR
ID  - 1204559
AU  - Majtner, Tomáš - Svoboda, David
PY  - 2014
TI  - Texture Analysis Using 3D Gabor Features and 3D MPEG-7 Edge Histogram Descriptor in Fluorescence Microscopy
PB  - IEEE Computer Society
CY  - Los Alamitos, California
SN  - 9781479980239
KW  - 3D images
KW  - Edge Histogram Descriptor
KW  - Gabor filters
KW  - fluorescence microscopy
N2  - The pattern recognition with focus on texture and shape analysis is still very hot topic, especially in biomedical image processing. In this article, we introduce 3D extension of well-known approaches for this particular area. We focus on the collection of MPEG-7 image descriptors, specifically on Edge Histogram Descriptor (EHD) and Gabor features, which are core of Homogeneous Texture Descriptor (HTD). The proposed extensions are evaluated on the dataset consisting of three classes of 3D volumetric biomedical images. Two different classifiers, namely $k$-NN and Multi-Class SVM, are used to evaluate the proposed algorithms. According to the presented tests, proposed 3D extensions clearly outperforms their 2D equivalents in the classification tasks.
ER  -

MAJTNER, Tomáš and David SVOBODA. Texture Analysis Using 3D Gabor Features and 3D MPEG-7 Edge Histogram Descriptor in Fluorescence Microscopy. Online. In \textit{4th International Conference on 3D Imaging (IC3D)}. Los Alamitos, California: IEEE Computer Society, 2014, p.~1-7. ISBN~978-1-4799-8023-9. Available from: https://dx.doi.org/10.1109/IC3D.2014.7032576.

Detailed Information on Publication Record