An Intensity Threshold based Image Segmentation of Malaria Infected Cells

Malaria is a perilous disease in charge for around 400 to 1000 deaths annually in India. The conventional technique to diagnose malaria is through microscopy. It takes few hours by an expert to examine and diagnose malarial parasites in the blood smear. The diagnosis report may vary when the blood smears are analyzed by different experts. In proposed work, an image processing based robust algorithm is designed to diagnose malarial parasites with minimal intervention of an expert. Initially, the images are enhanced by using green channel and histogram equalization, and the background subtraction is performed to get the clear vision of the region of interest. After preprocessing, a median filter is employed to eliminate the noise from the images. Then Otsu's method for segmentation is implemented on the filtered images. The database from world health organization is used in this research. The experiments give encouraging results and an accuracy up to 93%.