An automated system based on 2 d empirical mode decomposition and k-means clustering for classification of Plasmodium species in thin blood smear images

Methods In this work, thin blood smear sub images (n=87) of different Plasmodium species were acquired from the Parasite Image Library of the Centers for Disease Control and Prevention Database [http://www.dpd.cdc.gov/dpdx/HTML/ ImageLibrary/Malaria_il.htm]. The images were subjected to 2 d Empirical Mode Decomposition and four features namely the mean value of first Intrinsic Mode Function (IMF-1), IMF-2, IMF-3 and residue, were extracted. The significance of the extracted features was analyzed using ANOVA test. Further, the k-means clustering algorithm was used to classify the different Plasmodium species using the significant features.