EMPIRICAL STUDY ON MALARIA DETECTION USING MACHINE LEARNING

Abstract

Malaria is the third-deadliest infection on the world. Malaria is cause 14 million more cases and 69,000 more deaths in 2020 than it did in 2019. Between 2019 and 2020, India was the only high-burden country to show progress by sustaining a reduction in malaria burden. In 2020, 29 of the 85 malaria-endemic countries accounted for 96 percent of malaria cases. India was responsible for 1.7 percent of malaria cases and 1.2 percent of deaths worldwide. The gold standard for malaria diagnosis is currently microscopic examination of blood films. It is, however, subjective, error-prone, and time-consuming. To address such issues, computational microscopic imaging methods have recently received a lot of attention in the field of digital pathology. As a result, over the last decade, researchers have focused on digital image analysis and computer vision methods for malaria diagnosis. Various contrast enhancement and segmentation methods for microscopic imaging have been discussed in this study for accurate malaria diagnosis.