Towards Automated TEM for Virus Diagnostics: Segmentation of Grid Squares and Detection of Regions of Interest
2009 (English)In: Proceedings of the 16th Scandinavian Conference on Image Analysis (SCIA), Berlin: Springer-Verlag , 2009, 169-178 p.Conference paper (Refereed)
When searching for viruses in an electron microscope thesample grid constitutes an enormous search area. Here, we present methodsfor automating the image acquisition process for an automatic virusdiagnostic application. The methods constitute a multi resolution approachwhere we first identify the grid squares and rate individual gridsquares based on content in a grid overview image and then detect regionsof interest in higher resolution images of good grid squares. Our methodsare designed to mimic the actions of a virus TEM expert manually navigatingthe microscope and they are also compared to the expert’s performance.Integrating the proposed methods with the microscope wouldreduce the search area by more than 99.99% and it would also removethe need for an expert to perform the virus search by the microscope.
Place, publisher, year, edition, pages
Berlin: Springer-Verlag , 2009. 169-178 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 5575
TEM, virus diagnostics, automatic image acquisition
Computer Vision and Robotics (Autonomous Systems)
Research subject Computerized Image Analysis
IdentifiersURN: urn:nbn:se:uu:diva-108568DOI: 10.1007/978-3-642-02230-2_18ISBN: 978-3-642-02229-6OAI: oai:DiVA.org:uu-108568DiVA: diva2:236392