. "43536" . "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%." . . . . . "6"^^ . "RIV/00216224:14330/14:00073550" . "[8984A2F7556C]" . "2014-01-01+01:00"^^ . . . . . . "IEEE Computer Society" . . "RIV/00216224:14330/14:00073550!RIV15-MSM-14330___" . "14330" . . "texture descriptor; rsurf; hep-2"@en . "RSurf - the Efficient Texture-Based Descriptor for Fluorescence Microscopy Images of HEp-2 Cells"@en . . "Stoklasa, Roman" . . . . "RSurf - the Efficient Texture-Based Descriptor for Fluorescence Microscopy Images of HEp-2 Cells"@en . "RSurf - the Efficient Texture-Based Descriptor for Fluorescence Microscopy Images of HEp-2 Cells" . . . "Stockholm, Sweden" . "RSurf - the Efficient Texture-Based Descriptor for Fluorescence Microscopy Images of HEp-2 Cells" . "Svoboda, David" . "9781479952083" . "1051-4651" . "10.1109/ICPR.2014.215" . "3"^^ . "P(GBP302/12/G157), S" . "3"^^ . "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%."@en . "Majtner, Tom\u00E1\u0161" . "22nd International Conference on Pattern Recognition" . "Los Alamitos, California" . .