Virus texture analysis using local binary patterns and radial density profiles

Authors:
Gustaf Kylberg;Mats Uppström;Ida-Maria Sintorn
Affiliations:
Centre for Image Analysis, Uppsala, Sweden;Vironova AB, Stockholm, Sweden;Centre for Image Analysis, Uppsala, Sweden
Venue:
CIARP'11 Proceedings of the 16th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Year:
2011

Citing 3
Cited 0

Texture classification by center-symmetric auto-correlation, using Kullback discrimination of distributions

Pattern Recognition Letters
Random Forests

Machine Learning
Robust Texture Classification by Subsets of Local Binary Patterns

ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.