DEVELOPMENT OF AN APPROPRIATE ALGORITHM TO IDENTIFY AND CLASSIFY MALARIA PARASITE BY USING IMAGE PROCESSING

Abstract

Malaria is a mosquito borne infectious disease of humans and other animals caused by protozoan parasite of the genus plasmodium. The vast majority of deaths are caused by P.f Maintaining one’s health is the most essential components of human life and health. So the security of human health from different types of diseases may be ensured by using modern technology that could facilitate accurate screening of pathogens. Identification of malaria at early stage is helpful as its effect increases drastically and cause great harm to human life if it is left unattended. It will be speared out through the blood cell. One of the important requirements in image processing, indexing, classification and clustering and is extracting efficient features from images. The color feature is one of the most widely used visual features. In this paper color features extraction based on partial domain is presented. The shape, size and stage differentiation is applied on the images and different size and stage are specified. Pixels area of P.v is greater than from the area of P.f. pixels area of P.v is 5741 and pixels area of P.f is 3762 at trophozoite stage. The image retrieval results in compare to global color histogram show the acceptable efficiency of this approach.The system achieved hi gh percentages of sensitivity 91.9%, specificity 99.33%, and positive predicted value 87.2% an d accuracy 98.98%. These results show the potential of digital image analysis to be efficiently applied in automatic malaria diagnosis