Local Intensity and PCA Based Detection of Virus Particle Candidates in Transmission Electron Microscopy Images
2009 (English)In: Proc. 6th International Symposium on Image and Signal Processing and Analysis: ISPA 2009, Piscataway, NJ: IEEE , 2009, 426-431 p.Conference paper (Refereed)
We present a general method using local intensity informationand PCA to detect objects characterized onlyby that they differ from their surroundings. We apply ourmethod to the problem of automatically detecting virus particlecandidates in transmission electron microscopy images.Viruses have very different shapes and sizes, manyspecies are spherical whereas others are highly pleomorphic.To detect any kind of virus particles in electron microscopyimages it is therefore necessary to use a methodnot restricted to detection of a specific shape. The methodproposed here uses only one input parameter, the approximatevirus thickness, which is a conserved feature withina virus species. It is capable to detect virus particles ofvery varying shapes. Results on images with highly texturedbackground of several different virus species are presented.
Place, publisher, year, edition, pages
Piscataway, NJ: IEEE , 2009. 426-431 p.
Computer Vision and Robotics (Autonomous Systems)
Research subject Computerized Image Analysis
IdentifiersURN: urn:nbn:se:uu:diva-108567ISBN: 978-953-184-135-1OAI: oai:DiVA.org:uu-108567DiVA: diva2:275523