Automatic Classification of Red Blood Cells using Gaussian Mixture Densities [chapter]

J. Dahmen, J. Hektor, R. Perrey, H. Ney
2000 Informatik aktuell  
In this paper we present an invariant statistical approach to classifying red blood cells (RBC). Given a database of 5062 grayscale images, we model the distribution of the observations by using Gaussian mixture densities within a Bayesian framework. As invariance is of great importance when classifying RBC, we use a Fourier-Mellin based approach to extract features which are invariant with respect to 2D rotation, shift and scale. To prove the e ciency of our approach, we also apply it to the
more » ... dely used US Postal Service handwritten digits recognition task, obtaining state-of-the-art results.
doi:10.1007/978-3-642-59757-2_62 fatcat:xuva4zx2v5d5fhcjsykzx3tbci