Automatic segmentation of malaria parasites on thick blood film using blob analysis

Malaria remains a public health problem in Indonesia. There are still many deaths caused by malaria, particularly in eastern Indonesia. There are two types of blood perform in malaria, thick blood film and thin blood film. In Indonesia, thin blood film is used more frequently than thick blood film. Malaria parasites can be found in thick blood film rapidly due to the higher volume of the blood used and sweeping process is not as much on thin blood, still a lot of leukocytes or white blood cells and platelets in the thick blood film, making it more difficult to identify the malaria parasite. Therefore we need a method can identify malaria parasites in thick blood film with a high percentage of accuracy. This study aims to build a segmentation system more objective and reduce subjective factors of medical personnel in the diagnosis of malaria parasites. This study has two main stages, preprocessing and segmentation. We use the HSV color space in the preprocessing and morphological operations and blob analysis on the segmentation stage. From the results can be known that the blob analysis was able to identify malaria parasites automatically.