Plasmodium knowlesi (PK) is the fifth most prevalent malarial parasite species that causes serious health problems. Generally, PK present in a thin blood smear is observed using a microscope to differentiate between trophozoites (PKT), schizonts (PKS), gametocytes (PKG), and white blood cells (WBCs). This process is time-consuming and strenuous for the human eye. This study developed an intelligent classification procedure for PK using image processing and classification methods. The processes involved starting from image acquisition, and contrast enhancement based on Combination Local and Global Statistical Data (CLGSD), and local contrast stretching (LCS). Subsequently, a segmentation procedure was developed to segment the malaria images into two regions, namely malarial parasites and background regions. The proposed 16 feature sets were extracted, which consisted of the size of the object, size ratio of the object per infected RBC, and seven moments for each object shape based on size and perimeter. Finally, to validate the procedure performance, the proposed procedure was tested using 800 malarial parasites and WBC images. The results showed that the proposed procedure can classify three stages of PK, namely PKT, PKS, and PKG, as well as WBCs with an accuracy of 99.56% for training and 98.84% for validation, using a multi-layer perceptron (MLP) trained using the Levernberg-Marquardt (LM) algorithm.
