RSURF - The efficient texture-based descriptor for fluorescence microscopy images of hep-2 cells

Tomas Majtner, Roman Stoklasa, David Svoboda

Publikation: Kapitel i bog/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Abstrakt

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 kNN classifier based solely on the proposed descriptor achieve the accuracy as high as 91.1%.

OriginalsprogEngelsk
TitelProceedings - International Conference on Pattern Recognition
Antal sider6
ForlagIEEE
Publikationsdato4. dec. 2014
Sider1194-1199
Artikelnummer6976925
ISBN (Elektronisk)9781479952083
DOI
StatusUdgivet - 4. dec. 2014
Udgivet eksterntJa
Begivenhed22nd International Conference on Pattern Recognition, ICPR 2014 - Stockholm, Sverige
Varighed: 24. aug. 201428. aug. 2014

Konference

Konference22nd International Conference on Pattern Recognition, ICPR 2014
LandSverige
ByStockholm
Periode24/08/201428/08/2014
NavnProceedings - International Conference on Pattern Recognition
ISSN1051-4651

Fingeraftryk

Dyk ned i forskningsemnerne om 'RSURF - The efficient texture-based descriptor for fluorescence microscopy images of hep-2 cells'. Sammen danner de et unikt fingeraftryk.

Citationsformater