Malays. Appl. Biol. (2018) 47(2): 71–76
MALARIA PARASITES SEGMENTATION BASED ON SAUVOLA
ALGORITHM MODIFICATION
WAN AZANI MUSTAFA1*, AIMI SALIHAH ABDUL-NASIR2 and ZEEHAIDA MOHAMED3
1,2Faculty of Engineering Technology, Universiti Malaysia Perlis, UniCITI Alam Campus,
Sungai Chuchuh, 02100 Padang Besar, Perlis, Malaysia
3Department of Microbiology & Parasitology, School of Medical Sciences, Health Campus,
Universiti Sains Malaysia, 16150 Kubang Kerian, Kelantan, Malaysia
*E-mail: This e-mail address is being protected from spambots. You need JavaScript enabled to view it
Accepted 25 April 2018, Published online 25 May 2018
ABSTRACT
Malaria is a serious disease caused by a blood parasite of the genus Plasmodium and becomes a leading cause of death in the world, particularly in Africa and South Asia. In general, the conventional malaria diagnosis based on manual microscopic observation under a light microscope will increase the chance of false detection and delay diagnosis process. As a result, many researchers have proposed automated malaria detection based on image processing approach in order to provide prompt detection of malaria parasite as well as increasing the accuracy of malaria diagnosis. This paper proposed a new method based on algorithm modification that has been inspired by the Sauvola’s segmentation method. The objective of the proposed method is to improve the Sauvola method and achieve better segmentation results compared to the Feng method, Bradley method, and Nick method. Overall, the results of the numerical simulation indicate that the proposed method is the most effective and efficient (specificity = 99.94% and accuracy = 98.04%) compared to other methods. Hence, the implications of this image analysis would give future research directions for the researchers.
Key words: Algortihm, Malaria, Plasmodium, Parasites, Segmentation, Sauvola
