Virus recognition based on local texture
2014 (English)In: Proceedings 22nd International Conference on Pattern Recognition (ICPR), 2014, 2014, 3227-3232 p.Conference paper (Refereed)
To detect and identify viruses in electron microscopy images is crucial in certain clinical emergency situations. It is currently a highly manual task, requiring an expert sittingat the microscope to perform the analysis visually. Here wefocus on and investigate one aspect towards automating the virusdiagnostic task, namely recognizing the virus type based on theirtexture once possible virus objects have been segmented. Weshow that by using only local texture descriptors we achievea classification rate of almost 89% on texture patches from 15different virus types and a debris (false object) class. We compareand combine 5 different types of local texture descriptors andshow that by combining the different types a lower classificationerror is achieved. We use a Random Forest Classifier and comparetwo approaches for feature selection.
Place, publisher, year, edition, pages
2014. 3227-3232 p.
, International Conference on Pattern Recognition, ISSN 1051-4651
Computer Vision and Robotics (Autonomous Systems) Medical Image Processing
Research subject Computerized Image Analysis; Computerized Image Processing
IdentifiersURN: urn:nbn:se:uu:diva-216290DOI: 10.1109/ICPR.2014.556ISI: 000359818003060ISBN: 978-1-4799-5208-3OAI: oai:DiVA.org:uu-216290DiVA: diva2:692853
IEEE 22nd International Conference on Pattern Recognition (ICPR 2014), Stockholm, Sweden