Virus texture analysis using local binary patterns and radial density profiles
2011 (English)In: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications / [ed] San Martin, César; Kim, Sang-Woon, Springer Berlin/Heidelberg, 2011, 573-580 p.Conference paper (Refereed)
We investigate the discriminant power of two local and two global texture measures on virus images. The viruses are imaged using negative stain transmission electron microscopy. Local binary patterns and a multi scale extension are compared to radial density profiles in the spatial domain and in the Fourier domain. To assess the discriminant potential of the texture measures a Random Forest classifier is used. Our analysis shows that the multi scale extension performs better than the standard local binary patterns and that radial density profiles in comparison is a rather poor virus texture discriminating measure. Furthermore, we show that the multi scale extension and the profiles in Fourier domain are both good texture measures and that they complement each other well, that is, they seem to detect different texture properties. Combining the two, hence, improves the discrimination between virus textures.
Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2011. 573-580 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 7042
virus morphology, texture analysis, local binary patterns, radial density proﬁles
Computer Vision and Robotics (Autonomous Systems)
Research subject Computerized Image Processing
IdentifiersURN: urn:nbn:se:uu:diva-163119DOI: 10.1007/978-3-642-25085-9_68ISBN: 978-3-642-25084-2OAI: oai:DiVA.org:uu-163119DiVA: diva2:462774
16th Iberoamerican Congress on Pattern Recognition