Feature extraction and classification for detection malaria parasites in thin blood smear

Malaria is caused by Plasmodium parasites that are able to invade human red blood cell. Many researches have focused on improving the accuracy of the diagnosis. Image processing method is able to increase results of malaria parasite cell detection. This paper is developed based on the image processing technique to detect three stages of Plasmodium parasites while in human host, i.e. trophozoite, schizont, and gametocyte plasmodium falciparum. Feature extraction based on histogram-based texture is used to extract feature parasite cell. Multilayer perceptron backpropagation algorithm is used to classify all features. The results show that the proposed method achieves accuracy of 87.8%, sensitivity of 81.7%, and specificity of 90.8% for detecting infected red blood cells thus improving decision-making for malaria diagnosis.