Automated classification of malaria parasite species on thick blood film using support vector machine

Malaria is a serious global health problem. It requires fast and effective diagnosis for detecting and classifying the type of infection. Proper treatment should be administered in a timely fashion to prevent an outbreak. Microscopic examination of thick blood films is one of the current standards for malaria diagnosis. However, inspecting a thick blood film is time-consuming and requires experienced technicians. Hence, for developing countries where most cases of malaria occur but microscopy expertise may not be available, a computerized system to aid such diagnosis is desirable. In this paper, an automated classification system operating on digitized images of thick blood film has been developed to classify between Plasmodium falciparum and Plasmodium vivax malaria parasite species. The system is fully automated. It is fast and can be handled by non-experts. We calculate five statistical features - mean, standard deviation, kurtosis, skewness and entropy - from four color channels (green, intensity, saturation, and value) of these images. The features are then projected onto a subspace representing image characteristics from both species. The projected features are used by the support vector machine for classification. It is found that the algorithm has acceptable training error and can classify test images with good accuracy.