Chromatin detection in malaria thick blood film using automated image processing

摘要

Malaria is a serious global health problem and rapid, accurate diagnosis is required to control the disease. An image processing algorithm to aid the diagnosis of malaria on thick blood films is developed. Morphological and automatic threshold selection techniques are applied on two color components from the HSI color model to identify chromatins of P. Falciparum and P. Vivax malaria species on the images. Chromatins are positively identified with good sensitivities for both species. After identifying the position of chromatins, the algorithm splits the image into small subimages, each with a chromatin in the center. These small images can subsequently be used by technician to classify malaria species more conveniently.